{ "complete": true, "report": { "bucket": "emo_Pride", "label": "Intense Pride", "definition": { "id": "emo_Pride", "category": "emotion", "head": "emo_Pride", "pole": "high", "label": "Intense Pride", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_pride/full-v2-sealed/sealed-selected", "mission": "emotion_pride", "format_status": "CANONICAL", "heldout": true, "qualified": false, "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": 6.336428580284118, "genuineness": 4.026163122653961, "wer": 0.002290994623655914, "identity": 0.5278961291909218, "voiceclap": 0.029233549321070314, "fitness": 0.7389083635722544, "steering_v2": 0.8288761745453846, "raw_target": 0.9284950366616249, "target_cdf": 0.8288761745453846, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.343974142074585, "genuineness": 3.98028525352478, "wer": 0.0013333333333333333, "identity": 0.5278961291909218, "fitness": 0.7387873015140027, "steering_v2": 0.8308649783610623 }, "none": { "n": 50, "ce": 6.328883018493652, "genuineness": 4.072040991783142, "wer": 0.0032486559139784945, "identity": null, "fitness": 0.7390294256305062, "steering_v2": 0.826887370729707 } } } } ], "selected_wording": { "id": "manual-b8282fc33fc9", "general": "Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.", "inline": [ "Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.", "Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.", "Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority." ], "cfg": 3, "recipe": "P05", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-3", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 1.5705078240315444, "target_raw": 1.0368591383099557, "ce": 6.212840628623963, "genuineness": 4.153692269325257, "identity": 0.5415620688349009, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.029216949269175528, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 2.0173827541705376, "target_raw": 1.2691948056221007, "ce": 6.1461221933364865, "genuineness": 4.034133732318878, "identity": 0.5568738929927349, "wer": 0.006666666666666666, "valid_fraction": 1, "identity_delta": -0.013905125111341477, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 1.5705078240315444, "target_raw": 1.0368591383099557, "ce": 6.212840628623963, "genuineness": 4.153692269325257, "identity": 0.5415620688349009, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.029216949269175528, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 1.3991211069720912, "target_raw": 0.9477531164884567, "ce": 6.196955275535584, "genuineness": 4.177855014801025, "identity": 0.5739413857460022, "wer": 0.006666666666666666, "valid_fraction": 1, "identity_delta": 0.0031623676419258117, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 1.3699218857926299, "target_raw": 0.9325720891356468, "ce": 6.164787435531617, "genuineness": 4.1160360217094425, "identity": 0.5211581788957119, "wer": 0.009236111111111112, "valid_fraction": 1, "identity_delta": -0.049620839208364485, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 1.2882812696148211, "target_raw": 0.8901261478662491, "ce": 6.19060115814209, "genuineness": 4.186327660083771, "identity": 0.5363414540886879, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.034437564015388486, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 2.883398419430182, "target_raw": 1.7194467976689338, "ce": 6.042271709442138, "genuineness": 4.000243091583252, "identity": 0.466694264113903, "wer": 0.04522639318885449, "valid_fraction": 0.9, "identity_delta": -0.10408475399017333, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 2.249804710182436, "target_raw": 1.3900337845087052, "ce": 6.157440495491028, "genuineness": 4.117918872833252, "identity": 0.5001296855509281, "wer": 0.009444444444444445, "valid_fraction": 1, "identity_delta": -0.07064933255314827, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 2.20156253636355, "target_raw": 1.3649520963430404, "ce": 6.11216721534729, "genuineness": 3.9807873487472536, "identity": 0.49533359706401825, "wer": 0.009215686274509804, "valid_fraction": 1, "identity_delta": -0.07544542104005814, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 2.011328150750051, "target_raw": 1.2660469442605973, "ce": 6.149299192428589, "genuineness": 4.086538624763489, "identity": 0.485724913328886, "wer": 0.009399509803921569, "valid_fraction": 1, "identity_delta": -0.08505410477519035, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 2.0173827541705376, "target_raw": 1.2691948056221007, "ce": 6.1461221933364865, "genuineness": 4.034133732318878, "identity": 0.5568738929927349, "wer": 0.006666666666666666, "valid_fraction": 1, "identity_delta": -0.013905125111341477, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 1.6532226631801223, "target_raw": 1.0798635810613633, "ce": 6.202515172958374, "genuineness": 4.161537301540375, "identity": 0.5429107539355755, "wer": 0.008596491228070175, "valid_fraction": 1, "identity_delta": -0.0278682641685009, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 1.6366211141373228, "target_raw": 1.0712322354316712, "ce": 6.1759072065353395, "genuineness": 4.127332854270935, "identity": 0.5432569369673729, "wer": 0.009444444444444445, "valid_fraction": 1, "identity_delta": -0.027522081136703493, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 1.6311523429103245, "target_raw": 1.0683889552950858, "ce": 6.236668658256531, "genuineness": 4.183817279338837, "identity": 0.5461550019681454, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.024624016135931015, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 1.4747070394788206, "target_raw": 0.9870511546730996, "ce": 6.20886926651001, "genuineness": 4.158399307727814, "identity": 0.5464121706783771, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.024366847425699233, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 1.4318359375223912, "target_raw": 0.9647619515657425, "ce": 6.171141576766968, "genuineness": 4.110387563705444, "identity": 0.5773950286209584, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.006616010516881943, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 1.40029297198555, "target_raw": 0.9483623832464219, "ce": 6.209266424179077, "genuineness": 4.146474826335907, "identity": 0.5503503203392028, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.020428697764873504, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 1.3068359432545766, "target_raw": 0.8997729465365409, "ce": 6.2140320301055905, "genuineness": 4.250970852375031, "identity": 0.5590663939714432, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.01171262413263321, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 1.2937500121808936, "target_raw": 0.8929694131016731, "ce": 6.167170238494873, "genuineness": 4.198879754543304, "identity": 0.5503410406410694, "wer": 0.0029411764705882353, "valid_fraction": 1, "identity_delta": -0.020437977463006973, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 1.1999023579573107, "target_raw": 0.8441768854856491, "ce": 6.190601134300232, "genuineness": 4.283606338500976, "identity": 0.5374271817505359, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03335183635354042, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 1.189648434477168, "target_raw": 0.8388457469642162, "ce": 6.2199890375137326, "genuineness": 4.241870594024658, "identity": 0.5337620791047811, "wer": 0.008888888888888889, "valid_fraction": 1, "identity_delta": -0.037016938999295236, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 2.799999959874704, "target_raw": 1.6760869324207306, "ce": 6.088140630722046, "genuineness": 3.974197494983673, "identity": 0.47067789174616337, "wer": 0.018489422084623324, "valid_fraction": 1, "identity_delta": -0.10010112635791302, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 2.73789059826473, "target_raw": 1.6437955260276795, "ce": 6.057958507537842, "genuineness": 4.0225230097770694, "identity": 0.43041273653507234, "wer": 0.029368550051599586, "valid_fraction": 0.95, "identity_delta": -0.14036628156900405, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 2.323242182417164, "target_raw": 1.4282148122787475, "ce": 6.037803983688354, "genuineness": 4.046685779094696, "identity": 0.4877128578722477, "wer": 0.028831914344685242, "valid_fraction": 1, "identity_delta": -0.0830661602318287, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 2.2453124826243136, "target_raw": 1.387698221206665, "ce": 6.133810997009277, "genuineness": 4.024405860900879, "identity": 0.4626086950302124, "wer": 0.012524509803921568, "valid_fraction": 1, "identity_delta": -0.10817032307386398, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 2.088867184924995, "target_raw": 1.3063604235649109, "ce": 6.083772158622741, "genuineness": 4.034761226177215, "identity": 0.5079418897628785, "wer": 0.030553405572755418, "valid_fraction": 0.95, "identity_delta": -0.06283712834119796, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 1.9222656358821955, "target_raw": 1.2197422683238983, "ce": 6.131428217887878, "genuineness": 4.072417497634888, "identity": 0.4743756964802742, "wer": 0.005572755417956656, "valid_fraction": 1, "identity_delta": -0.09640332162380219, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 1.9203124682938506, "target_raw": 1.2187267929315566, "ce": 6.128648281097412, "genuineness": 4.028799033164978, "identity": 0.4974161464720964, "wer": 0.02155637254901961, "valid_fraction": 1, "identity_delta": -0.07336287163197994, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 1.9128906183273782, "target_raw": 1.2148680835962296, "ce": 6.168560218811035, "genuineness": 4.047313284873963, "identity": 0.49847163036465647, "wer": 0.012524509803921568, "valid_fraction": 1, "identity_delta": -0.07230738773941994, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 1.9041015504758458, "target_raw": 1.21029854118824, "ce": 6.142150807380676, "genuineness": 4.0940698981285095, "identity": 0.5154696524143219, "wer": 0.018451797385620916, "valid_fraction": 1, "identity_delta": -0.05530936568975449, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 1.8085937551052274, "target_raw": 1.160642886161804, "ce": 6.1896082878112795, "genuineness": 4.119487822055817, "identity": 0.48825938776135447, "wer": 0.008388157894736842, "valid_fraction": 1, "identity_delta": -0.08251963034272194, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 1.7208984351936911, "target_raw": 1.1150490313768386, "ce": 6.1481078386306764, "genuineness": 4.106308174133301, "identity": 0.5103307815268636, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.06044823657721281, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 1.3843750204209098, "target_raw": 0.9400864481925965, "ce": 6.2025151491165165, "genuineness": 4.190720927715302, "identity": 0.4858740471303463, "wer": 0.0058823529411764705, "valid_fraction": 1, "identity_delta": -0.08490497097373009, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 1.138574227269908, "target_raw": 0.8122916504740715, "ce": 6.190601134300232, "genuineness": 4.189465677738189, "identity": 0.49436097517609595, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": -0.07641804292798042, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": 0.9932617217168537, "target_raw": 0.7367419257760048, "ce": 6.213237738609314, "genuineness": 4.320321094989777, "identity": 0.5707790181040764, "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": 0.8250488425170391, "target_raw": 0.6492860205471516, "ce": 6.202515125274658, "genuineness": 4.321576380729676, "identity": 0.5653451159596443, "wer": 0.019444444444444445, "valid_fraction": 0.95, "identity_delta": -0.005433902144432068, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": 0.8899902188857847, "target_raw": 0.683049825578928, "ce": 6.194175338745117, "genuineness": 4.335697412490845, "identity": 0.5512037724256516, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.019575245678424835, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": 0.8007812567174045, "target_raw": 0.6366690099239349, "ce": 6.191395354270935, "genuineness": 4.342287278175354, "identity": 0.5499021306633949, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.020876887440681457, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": 0.6489257902132568, "target_raw": 0.5577175208926201, "ce": 6.268836450576782, "genuineness": 4.341785192489624, "identity": 0.5516516341269017, "wer": 0.00981453634085213, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 1.2132421927350974, "target_raw": 0.8511124265193939, "ce": 6.2532688236236575, "genuineness": 4.150868048667908, "identity": 0.5154661053419113, "wer": 0.016608913588318622, "valid_fraction": 0.96, "identity_delta": -0.03618552878499031, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 1.6398242259801665, "target_raw": 1.0728975719213485, "ce": 6.249615211486816, "genuineness": 4.041288371086121, "identity": 0.5544497139751912, "wer": 0.0066012858232537865, "valid_fraction": 1, "identity_delta": 0.0027980798482894896, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 1.5525781293976608, "target_raw": 1.0275372737646102, "ce": 6.232459020614624, "genuineness": 4.058798542022705, "identity": 0.5445647957921028, "wer": 0.004552983248635422, "valid_fraction": 1, "identity_delta": -0.007086838334798813, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.08724609658250555, "ci95_z": [ -0.056757816436399086, 0.29349608038908237 ], "language_deltas": { "en": 0.4781249724138587, "de": 0.10898442072313348, "fr": -0.07587893601929782, "nl": -0.01796873826693341, "es": -0.05703123593823319 }, "languages_improved": 2, "clear_gain": false, "delta_ce": 0.017156190872192383, "delta_genuineness": -0.01751017093658447, "delta_wer": 0.002048302574618364, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "adapter_vs_best_manual": { "n": 50, "delta_z": 0.42658203324506916, "ci95_z": [ 0.22996093057211678, 0.6064453160423113 ], "language_deltas": { "en": 0.4919921774015018, "de": 0.7253906455552578, "fr": 0.2596679551472558, "nl": 0.11113283227156068, "es": 0.5447265558497696 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.0036536121368408205, "delta_genuineness": -0.1095796775817871, "delta_wer": -0.010007627765064836, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.5643164025218405, "ci95_z": [ 0.4252148417280612, 0.7332031353448031 ], "language_deltas": { "en": 0.5067382639526834, "de": 0.8841797162728828, "fr": 0.6209960600398249, "nl": 0.42373043848809255, "es": 0.38593753385571883 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.015567626953125, "delta_genuineness": -0.19091714382171632, "delta_wer": 0.006794377247466492, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 2.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793033839.2440019, "example": { "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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.", "language": "de", "seed": 1702, "scale": 0.0, "cfg": 2.0, "frames": 128, "reference": true } }, "rows": [ { "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": "009d42b80103006c8ed4f616b944a6d7d685e557b5aeff133569b37bff66a849", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9dbf78fba462d3df3bd04aa5ea9a1ea6de506f21f3575dd4ac4832b569200455", "generation_seconds_batch": 13.924845490022562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41733109951019287, "target_z": 0.37890624059563366, "ce": 6.332377910614014, "genuineness": 4.137060642242432, "identity": 0.2242404967546463, "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_Pride/009d42b80103006c8ed4f616b944a6d7d685e557b5aeff133569b37bff66a849.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": "00b5459ddfacfb3cfa3332dbaf0bea1fbdca2f5f0753146ee767f4f7bd05c5ea", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ec26f7b011b410f4fc0cc438c1c58657f28e3148210e05499cdd962ec6203b8f", "generation_seconds_batch": 16.119979920913465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6663386821746826, "target_z": 2.7812501540524774, "ce": 6.41180419921875, "genuineness": 4.168440818786621, "identity": 0.41628772020339966, "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_Pride/00b5459ddfacfb3cfa3332dbaf0bea1fbdca2f5f0753146ee767f4f7bd05c5ea.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "0143562b16d372baeb20922f08d563924ffc479644157b02b96bcfc2493ce9a4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4126adbf28c89af776ccb276df33162b17d4c0e473a41257fe8b1b004774a551", "generation_seconds_batch": 14.21336897497531, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3487231731414795, "target_z": 4.09374997492169, "ce": 6.483288764953613, "genuineness": 4.256305694580078, "identity": 0.466530442237854, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinkommen.", "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_Pride/0143562b16d372baeb20922f08d563924ffc479644157b02b96bcfc2493ce9a4.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "0177daffed3d9d40615345a3c0a5c135aa594504a13a42bfd6cbb5308ad8cc7c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3be609ea9dd91955626989abae23a69c3413351ffd1bc7505a234eb46b23aa2e", "generation_seconds_batch": 19.485182320931926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.162673830986023, "target_z": 1.8125000788175465, "ce": 6.125868320465088, "genuineness": 3.8044304847717285, "identity": 0.3726732134819031, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0177daffed3d9d40615345a3c0a5c135aa594504a13a42bfd6cbb5308ad8cc7c.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "018c7c6e45896ebf5e44f59ba744c253bffef4ebd4b69b1db1fd1b35761bdc05", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "271a301679eb71a4a8c66728583e772ed62363d2c96388e53bc498b2cf5a213c", "generation_seconds_batch": 19.093130009016022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5777727365493774, "target_z": 0.6875000358261575, "ce": 6.340320587158203, "genuineness": 4.331617832183838, "identity": 0.30645617842674255, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/018c7c6e45896ebf5e44f59ba744c253bffef4ebd4b69b1db1fd1b35761bdc05.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "01edbcde2c8332325cdffb0e27b5c7d9b736b44d20817484d66fe06f44ce5355", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e230bbe91fd5b035637a34a8e5ad242b31d1828c4fbb30850c2612648ecb9111", "generation_seconds_batch": 20.14193001005333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8986559510231018, "target_z": 1.3046875116435013, "ce": 5.919358730316162, "genuineness": 4.005263805389404, "identity": 0.7039872407913208, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/01edbcde2c8332325cdffb0e27b5c7d9b736b44d20817484d66fe06f44ce5355.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "9de0cefe980a97dc398e12a1cdaf5c0e5240b950985039944490ad9aa104e7fb", "generation_seconds_batch": 16.252383232000284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3088990449905396, "target_z": 2.09374997492169, "ce": 6.0146708488464355, "genuineness": 4.65797233581543, "identity": 0.5494189262390137, "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_Pride/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "022db8c05c6d95251af9999ad9339cc8f94a5be41aa12fa9d3ee0ae84d5da064", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5637f973d69b6368dc31073f0e1b004b9e35af66a4fa14e7b61fbdb30e64ee1a", "generation_seconds_batch": 16.544644084060565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0562727451324463, "target_z": 3.531250182713403, "ce": 6.23706579208374, "genuineness": 4.20609712600708, "identity": 0.6454976201057434, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/022db8c05c6d95251af9999ad9339cc8f94a5be41aa12fa9d3ee0ae84d5da064.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "022ded5fdee72816876004e0b565eac12fe8736bd4a3d79888929468aa4c96a5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "b3d9f7f5052f4ec913a14007c1b10115a87ab15ad86aa165c38197b58ce0290d", "generation_seconds_batch": 22.624385284027085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2276628017425537, "target_z": 1.9375000071652315, "ce": 5.863759994506836, "genuineness": 3.936227321624756, "identity": 0.5823994874954224, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/022ded5fdee72816876004e0b565eac12fe8736bd4a3d79888929468aa4c96a5.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "024bd76dc23394d17d58e1c46adfeaa972ed818ff98841775c23bb8645b402a7", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "71bf934bcb29a5dfe9517450acd89672f0298d542c3556755fb27fce40bbc56b", "generation_seconds_batch": 16.9485589240212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0562727451324463, "target_z": 3.531250182713403, "ce": 6.372091293334961, "genuineness": 4.005263805389404, "identity": 0.5901956558227539, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/024bd76dc23394d17d58e1c46adfeaa972ed818ff98841775c23bb8645b402a7.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "024ecc27a26b47cf1316230f10223eec12c2bead4375720659df7bea0c099d91", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6add3cb9fdf03365a47ecae1f3b845d67f8a42caafac4f16f159d4ecacdbdb4c", "generation_seconds_batch": 18.61935680406168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42647019028663635, "target_z": 0.3964843877630686, "ce": 6.260893821716309, "genuineness": 4.268857479095459, "identity": 0.6531765460968018, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/024ecc27a26b47cf1316230f10223eec12c2bead4375720659df7bea0c099d91.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "035049ae02c20efc17fa54eb41bd709e231e82604c962c81cd7aa433ea993e77", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "087b5a517b059c0ad9f6921e83d02dd95a288c0fe83190d4286e7186e4d71356", "generation_seconds_batch": 21.80047111492604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4632480144500732, "target_z": 2.390625120017628, "ce": 6.054384231567383, "genuineness": 4.049196243286133, "identity": 0.5817075967788696, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/035049ae02c20efc17fa54eb41bd709e231e82604c962c81cd7aa433ea993e77.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": "03a065d3b2a594efb4fa1fedd4046b953fa7684ca4084dc9b52855646c212383", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3cadb324a2ef6f1a7dcbfb5888b9ab7fd7a44fd35bfb692c307b403b4ce03c3c", "generation_seconds_batch": 13.789946026052348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6427617073059082, "target_z": 0.8124999641738425, "ce": 6.173524379730225, "genuineness": 4.331617832183838, "identity": 0.7885323166847229, "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_Pride/03a065d3b2a594efb4fa1fedd4046b953fa7684ca4084dc9b52855646c212383.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "03c4551c52e996a3abebb4cbcd60b1193db91a1dc74409f9e757f5e617f80462", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2efac9c9333afa7010a10a78180bc7f49854055132ad9c58c6259ec70b274f3e", "generation_seconds_batch": 15.003483689040877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7118125557899475, "target_z": 0.9453125170174248, "ce": 6.006728172302246, "genuineness": 3.8420867919921875, "identity": 0.5411823987960815, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/03c4551c52e996a3abebb4cbcd60b1193db91a1dc74409f9e757f5e617f80462.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "04667583aefec3223b596a245b5311b4283be101a3efdfcd9d483d019bd793c5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "9d006a867ef824e9ae34d5474f641a633dd993ef19d10e37d5616794c752c7d2", "generation_seconds_batch": 14.526363937999122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5526078939437866, "target_z": 2.5625001074784723, "ce": 5.935244083404541, "genuineness": 3.9550557136535645, "identity": 0.6200172305107117, "hypothesis": "De deur 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_Pride/04667583aefec3223b596a245b5311b4283be101a3efdfcd9d483d019bd793c5.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": "04d64d1e6f0554c32e0693a9e8df5d8424ede48a9237a0e718bf271089ad3a49", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "207c5241d0cffa907186a76fde74e0f1fe0a1dd2ec6991824f86906b223e3544", "generation_seconds_batch": 13.914176505990326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5655872821807861, "target_z": 0.6640625062695775, "ce": 6.300607204437256, "genuineness": 4.344170093536377, "identity": 0.6033748388290405, "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_Pride/04d64d1e6f0554c32e0693a9e8df5d8424ede48a9237a0e718bf271089ad3a49.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "04dd3a1fd49c82743d06b53fdb235ebbdb91d157d4653d47b9a84851dc0e1b84", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "91441891474cd0490aa623f14aa7fa9266f5ab794803306d8168f9648404e18a", "generation_seconds_batch": 18.40992855501827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7549045085906982, "target_z": 4.875000042991389, "ce": 6.316492557525635, "genuineness": 3.936227321624756, "identity": 0.43406063318252563, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/04dd3a1fd49c82743d06b53fdb235ebbdb91d157d4653d47b9a84851dc0e1b84.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "051cc93b11d7b6f5e26738de124ed86d091cc18180b10223b65f863f222833af", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b9d9bd7cfc3b641a2a91331f77dc55dedf75a984b4e21aae1abc82f3d9f2bcd5", "generation_seconds_batch": 18.964482816983946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6874416470527649, "target_z": 0.898437457904265, "ce": 6.0146708488464355, "genuineness": 4.049196243286133, "identity": 0.7292779088020325, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/051cc93b11d7b6f5e26738de124ed86d091cc18180b10223b65f863f222833af.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": "05307b3bc80204ad70dc6897786c44a483074b5584574d830c57006879ba463f", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "52039de7a11d5dbc720fca78a92d3ad08b421e3173490d272d34e7dfc1442c39", "generation_seconds_batch": 13.800161899067461, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3251463174819946, "target_z": 2.125000014330463, "ce": 6.316492557525635, "genuineness": 3.8797430992126465, "identity": 0.4761711359024048, "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_Pride/05307b3bc80204ad70dc6897786c44a483074b5584574d830c57006879ba463f.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "054162d6949d2b5b61849666d1bab6c2f8cb75caae965e31e21144f068b8d4e8", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dca09eff3ba4e64de7ff9943e1bcd667ac0047500f6d9f445b156a7842385881", "generation_seconds_batch": 19.573647512006573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45287197828292847, "target_z": 0.4472656444804731, "ce": 5.998785495758057, "genuineness": 4.143336772918701, "identity": 0.6670417189598083, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/054162d6949d2b5b61849666d1bab6c2f8cb75caae965e31e21144f068b8d4e8.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "afe833553f605f6d103ed3abdd8258af6bddca3064f28b08cf201c69f81be4a8", "generation_seconds_batch": 16.289771214011125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4396710693836212, "target_z": 0.4218749874608449, "ce": 6.427689552307129, "genuineness": 4.68307638168335, "identity": 0.5704250931739807, "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_Pride/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "0624a233fb026c018543abc53f6bae0e930a165413f98a64207ee93f364687c5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9f8432cd47e266d84b2b457767d599771017409bab623d39765c5be549fe31c5", "generation_seconds_batch": 19.787682521971874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.624483585357666, "target_z": 0.7773437844826766, "ce": 6.229123115539551, "genuineness": 4.507347106933594, "identity": 0.7051108479499817, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Chen. Shen", "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_Pride/0624a233fb026c018543abc53f6bae0e930a165413f98a64207ee93f364687c5.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "0625989acd5dc71fc0bd0d056260beea85fb0b3bb5fac50b59a56d93ee9ad14a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0837c53cda8a4d6789a939cfb470609516d348dbc37bcb7e7cad04454a4e5214", "generation_seconds_batch": 23.486162966000848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6590089797973633, "target_z": 0.8437500035826158, "ce": 6.300607204437256, "genuineness": 4.118232727050781, "identity": 0.16886624693870544, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0625989acd5dc71fc0bd0d056260beea85fb0b3bb5fac50b59a56d93ee9ad14a.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "06287e098347a505b70a21db7371a36860ee91756a228821f069a943de6c8638", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "bb6ae1757174332180d4b8d3eaaae47bff0fa642283e8203e4c5ceaa0163d139", "generation_seconds_batch": 18.523253292078152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2682809829711914, "target_z": 2.015625105687165, "ce": 6.09409761428833, "genuineness": 3.9801597595214844, "identity": 0.45124462246894836, "hypothesis": "Die Tür 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_Pride/06287e098347a505b70a21db7371a36860ee91756a228821f069a943de6c8638.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "0637eb21897ef1f30f3625a629bb63467c6430911612473c5360b98ca041fbf4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "39ed4f4e3662f42016dff8308ab0559e68d853f9b7c5101a75f9f975c3d84c1c", "generation_seconds_batch": 18.577518453937955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9798921942710876, "target_z": 1.4609374793999594, "ce": 6.141753673553467, "genuineness": 4.243753433227539, "identity": 0.6213418841362, "hypothesis": "La porte 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_Pride/0637eb21897ef1f30f3625a629bb63467c6430911612473c5360b98ca041fbf4.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "067623d7806509c4262ae20c2c9ce3374b0688407868755d582b8aaecac0018d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c51956292692e67de4d70b02efbbe65eba1b000d8f9244664cb0ea10b157ef34", "generation_seconds_batch": 19.93559719400946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.065190315246582, "target_z": 1.625000071652315, "ce": 6.292664527893066, "genuineness": 4.231201171875, "identity": 0.3682977259159088, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "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_Pride/067623d7806509c4262ae20c2c9ce3374b0688407868755d582b8aaecac0018d.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "07a6785983c4a6e038fe4e2334eab673b567f3f03d65687105dd181945963bd2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "46c9bbd9c6de273b59b169dd0dd519da8ac9a69cbb190284362a74862032bf05", "generation_seconds_batch": 18.42805007402785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4470007419586182, "target_z": 2.3593750806088543, "ce": 6.149696350097656, "genuineness": 4.268857479095459, "identity": 0.5370105504989624, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/07a6785983c4a6e038fe4e2334eab673b567f3f03d65687105dd181945963bd2.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "0864d2dc237c56a7e1fe72083258eb1b528a3a3edec2181b196c102c1eb87d3e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "13970101cf1f256944442a8e9bffc4ca6046a8c2a46086622a2151f240aa03c4", "generation_seconds_batch": 18.57349565299228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7321215867996216, "target_z": 0.9843749516346874, "ce": 6.348263263702393, "genuineness": 4.337893962860107, "identity": 0.33278825879096985, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0864d2dc237c56a7e1fe72083258eb1b528a3a3edec2181b196c102c1eb87d3e.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": "08676eeb73b2278929e3a1ec958a2217d27d57b4a9008ed5188e39cb7c00b433", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Someone moved the little blue chair.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "859067b33d00ab1a9d86f1c0953f6054adaaa33fd9e8dba94a39d607fcff7ff7", "generation_seconds_batch": 16.45845761091914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4681037664413452, "target_z": 0.47656249910434606, "ce": 6.467403411865234, "genuineness": 4.005263805389404, "identity": 0.1987173706293106, "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_Pride/08676eeb73b2278929e3a1ec958a2217d27d57b4a9008ed5188e39cb7c00b433.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "090462b8f6161303e1e3db7ff9e9e87144f691c00bbbbde33aa556adcfd76cc0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8dc8d50e03448daf0c9edf4c9052e8d13c96178cc525f1a995c451a5bd5fc248", "generation_seconds_batch": 13.803774839034304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4551243782043457, "target_z": 2.375000100313241, "ce": 6.141753673553467, "genuineness": 4.20609712600708, "identity": 0.3518577814102173, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/090462b8f6161303e1e3db7ff9e9e87144f691c00bbbbde33aa556adcfd76cc0.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "0912e3466c9b8863e19079d002a71d51e22297aeebda8823f50a6aa35d4c8648", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b44d3f853957c03a94cca5af4e8720cea917f2a88c4898046caa884ecea0cc56", "generation_seconds_batch": 21.478428832022473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9595831036567688, "target_z": 1.4218749301389928, "ce": 5.824047088623047, "genuineness": 4.149612903594971, "identity": 0.5554813146591187, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0912e3466c9b8863e19079d002a71d51e22297aeebda8823f50a6aa35d4c8648.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "098bbdc3618d038cf7e7c162916d8ade049b9983c0ce87e049f41be2ff90adcf", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "8001c8718bb9b45c223b68e01940260fbfdc2ef1fe43163d68c013c2d66c3277", "generation_seconds_batch": 18.629002745030448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9839540123939514, "target_z": 1.4687499892521527, "ce": 5.903473377227783, "genuineness": 4.093128204345703, "identity": 0.4553754925727844, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lento.", "wer": 0.06666666666666667, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/098bbdc3618d038cf7e7c162916d8ade049b9983c0ce87e049f41be2ff90adcf.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "09a292060016d9f63cfd5a8f8d6ac6d1af4a67f8b3bc6f962cee6b83ba733ac3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a7d01306fa28e0b69b141062ccd897fa4bae52a4fb13aa02e860bcb06a840838", "generation_seconds_batch": 14.160279094008729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.991283655166626, "target_z": 3.40625002507831, "ce": 6.062326908111572, "genuineness": 3.9927117824554443, "identity": 0.5139132738113403, "hypothesis": "J'ai trouvé la 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_Pride/09a292060016d9f63cfd5a8f8d6ac6d1af4a67f8b3bc6f962cee6b83ba733ac3.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "0a6622f21cb24ee8db2873c5f18147fb29be472be955660da46462d31b839662", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d194555a1e8ddf67060e769a2b6ce39fe8691139353f73b019a53020cb04df1b", "generation_seconds_batch": 18.61935680406168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5594945549964905, "target_z": 0.6523437414912876, "ce": 6.23706579208374, "genuineness": 4.193545341491699, "identity": 0.5213999152183533, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0a6622f21cb24ee8db2873c5f18147fb29be472be955660da46462d31b839662.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "0c0817c5eaa9136a6e082e05c49e8a66a9fae8e8e23c1ea8fc770880deb30659", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4682bdfdf8f28588ce293b7ee9ce4f99c2242daae31984226391b700787451dc", "generation_seconds_batch": 19.257681305985898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9067795276641846, "target_z": 1.3203124167041838, "ce": 6.157639026641846, "genuineness": 3.9425034523010254, "identity": 0.7554262280464172, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0c0817c5eaa9136a6e082e05c49e8a66a9fae8e8e23c1ea8fc770880deb30659.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "0c60d5a920a26f0305ff0d43b73596267da7fb894648e078fef1c8ff6f97587a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bd505ad307d8a7c0e3db345da5fe03d91f53508b2deb2824a31b23f8d2ebf705", "generation_seconds_batch": 13.916918847011402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5737109184265137, "target_z": 0.6796875259739642, "ce": 5.990842819213867, "genuineness": 4.055472373962402, "identity": 0.6924514174461365, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0c60d5a920a26f0305ff0d43b73596267da7fb894648e078fef1c8ff6f97587a.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "0c8fa43e9cf09088e778e4cd571bce6443efda60878e48df333e9d90976a8bb9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "78ab2edaaf98e3202f6c6b40ff38426502452dc8d0bc0437f14b1d953b71f698", "generation_seconds_batch": 18.966965776053257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4137120246887207, "target_z": 4.218749673981967, "ce": 6.213237762451172, "genuineness": 4.036643981933594, "identity": 0.5379049777984619, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0c8fa43e9cf09088e778e4cd571bce6443efda60878e48df333e9d90976a8bb9.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "0c90bcca14073e6cac0f00aaaa1dffb8ab322b41cf0e90db91de94e04e1cee08", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "99496245fe1fa19b4aa4c239a89f3811ac2529ac47b86adb46f0b2e237d1b4e7", "generation_seconds_batch": 21.732327883015387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8686351776123047, "target_z": 5.093749860277986, "ce": 6.213237762451172, "genuineness": 3.973883628845215, "identity": 0.4811970591545105, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0c90bcca14073e6cac0f00aaaa1dffb8ab322b41cf0e90db91de94e04e1cee08.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "0c9cf6581586d26686bee006c4dcf2b9e71ab2d959e605bc41f40cb1aba90b06", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04674f60375ca6d9b9fcc2964729c9530c3afbdf5c925b34ef017d1c79d594f2", "generation_seconds_batch": 21.81381840899121, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2682809829711914, "target_z": 2.015625105687165, "ce": 6.062326908111572, "genuineness": 4.1998209953308105, "identity": 0.5866977572441101, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0c9cf6581586d26686bee006c4dcf2b9e71ab2d959e605bc41f40cb1aba90b06.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "3920755ba0671f97ad7405f01d2faf6c9d48d25227620efd884f4038eb960c0b", "generation_seconds_batch": 14.993907129974104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49044376611709595, "target_z": 0.5195313032914093, "ce": 6.157639026641846, "genuineness": 3.986435890197754, "identity": 0.556948721408844, "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_Pride/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "0cef32cacc0aafd4d8f575aae844217a9f4253aff03ba81dc33410d983bed2bc", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c0bcbaae549fa6dd0f0a8fb16415f41d3ccec2dc15286455cf3c595fcae0d130", "generation_seconds_batch": 17.54473206703551, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3982590436935425, "target_z": 2.2656251916699426, "ce": 6.109982967376709, "genuineness": 4.118232727050781, "identity": 0.3502545654773712, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0cef32cacc0aafd4d8f575aae844217a9f4253aff03ba81dc33410d983bed2bc.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": "0d413e213ac3d51625d70a8f1be0d2a2880fc2d48c231437a10dfbedad0cb94a", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I wrote the number on the envelope.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa306477b76f65a1dd5fb483119aac5caa499d1427da752e006549b31223f67e", "generation_seconds_batch": 20.26234541798476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7711517810821533, "target_z": 4.906250082400162, "ce": 6.3641486167907715, "genuineness": 3.660081624984741, "identity": 0.39715129137039185, "hypothesis": "I wrote the number on the envelope. Rate it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0d413e213ac3d51625d70a8f1be0d2a2880fc2d48c231437a10dfbedad0cb94a.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "0d4a2e240e11aa16d7a9fe963db186dee608c4ee861e7ed53af513920eb00b4b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fcd61f70d222482f9db29f863cbcaedbb787e57b49c81a42cf67ddfc73e375d7", "generation_seconds_batch": 18.614575150073506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.544484257698059, "target_z": 2.5468750877740858, "ce": 6.340320587158203, "genuineness": 4.005263805389404, "identity": 0.5449705719947815, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0d4a2e240e11aa16d7a9fe963db186dee608c4ee861e7ed53af513920eb00b4b.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "0e45bbe915d02025d17d1fe62907345abfb214a0abf086077d78cd30e6fb362b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ab2d1c0710cf7caec5096c0b09f7089b4a0f3f4c794f2b6d39891c6e0b2a9e92", "generation_seconds_batch": 20.4511669150088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9189649820327759, "target_z": 1.3437499462607638, "ce": 6.1894097328186035, "genuineness": 4.369274139404297, "identity": 0.5312473773956299, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0e45bbe915d02025d17d1fe62907345abfb214a0abf086077d78cd30e6fb362b.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "0eda12f85154f83699f534593991a5c0ebbc2184f1336b00e27bd1342d32a0b3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bac98d7ef006a3e9594ac3a83285529692688557a5a459333d4b8e2b41e5fdd8", "generation_seconds_batch": 22.84072462504264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7638221979141235, "target_z": 2.9687501612177085, "ce": 6.38003396987915, "genuineness": 4.093128204345703, "identity": 0.4007907509803772, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0eda12f85154f83699f534593991a5c0ebbc2184f1336b00e27bd1342d32a0b3.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "0fe01d3c7ba0de67f6740e6cd44fad7871f686edcc6d1434775f115ef0e41c82", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d0bd0c2c5219b908b9b950f842d6db9523eb42e08985dedb27b33d5e75c698e0", "generation_seconds_batch": 18.57349565299228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5330927968025208, "target_z": 0.601562542095735, "ce": 6.316492557525635, "genuineness": 4.18726921081543, "identity": 0.2849920690059662, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/0fe01d3c7ba0de67f6740e6cd44fad7871f686edcc6d1434775f115ef0e41c82.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": "0ffd3eaf1f576f4cf5d8f2d7131ebe81a81d4c907f3b1aeab66c55554347962d", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4fc54bdbceef2b5b7bcfd752e4855cfd1caa492eb4dc066ac2b0c3060b2e0b06", "generation_seconds_batch": 16.939518630038947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.589958131313324, "target_z": 0.7109374507390335, "ce": 6.268836498260498, "genuineness": 3.7165660858154297, "identity": 0.6092910766601562, "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_Pride/0ffd3eaf1f576f4cf5d8f2d7131ebe81a81d4c907f3b1aeab66c55554347962d.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": "10357d35c6fe986b36c6b0703da425071f9117aaff43d7e3b5dfa0532653e998", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0d910a6cad21adf19711d64605186411bebf51a52d68c550b600f40c2f9f2364", "generation_seconds_batch": 17.86131543200463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8499141931533813, "target_z": 1.2109375080608855, "ce": 6.372091293334961, "genuineness": 4.080576419830322, "identity": 0.4871571958065033, "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_Pride/10357d35c6fe986b36c6b0703da425071f9117aaff43d7e3b5dfa0532653e998.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "1065becee438006fb30564aec9ace49d36861778d469def70ca1c2e4bb2ac356", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f4dd0f74bba96f0df683a697f880e6f21f1af0a3add4268052c404a21ce07721", "generation_seconds_batch": 18.88034257898107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4701346755027771, "target_z": 0.4804687540304427, "ce": 6.133810997009277, "genuineness": 3.9425034523010254, "identity": 0.7275797128677368, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1065becee438006fb30564aec9ace49d36861778d469def70ca1c2e4bb2ac356.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "10cb72e2b4ee1aca22412d4816c070f7deae1ffed2dd14c8d04304a0dc00053f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "26770099b60d29d51940e8c93819a71cbd42377619e59288f2199cf0692af5a1", "generation_seconds_batch": 21.187073144013993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9595831036567688, "target_z": 1.4218749301389928, "ce": 6.23706579208374, "genuineness": 4.1998209953308105, "identity": 0.6291279792785645, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/10cb72e2b4ee1aca22412d4816c070f7deae1ffed2dd14c8d04304a0dc00053f.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "110ef6cce8bdfbe50606b4e629c4a69cb52ae2843031a4b3239d8a6922aa1cbc", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a67babfd198330412f08fc6a9aaae5a1ebaa26b8e4b8e5c90a4b7718db7fd421", "generation_seconds_batch": 20.59252494201064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7280597686767578, "target_z": 0.9765624417824941, "ce": 6.340320587158203, "genuineness": 4.507347106933594, "identity": 0.7449151873588562, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/110ef6cce8bdfbe50606b4e629c4a69cb52ae2843031a4b3239d8a6922aa1cbc.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "112db5c800706f078ccd5a851782f76675ea6093b9fe30421a4abd31d3158056", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "47563536ecdca9df16a66789db132cc2b79a89a16a99507658eaba3a9c91d307", "generation_seconds_batch": 21.251813738956116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8620995879173279, "target_z": 1.2343749229737613, "ce": 6.046441555023193, "genuineness": 3.9927117824554443, "identity": 0.5948105454444885, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/112db5c800706f078ccd5a851782f76675ea6093b9fe30421a4abd31d3158056.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": "1159cc35ac2b79d2f089402bcd2ee81bbe1117265934eb16e57a6721f4440655", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "073d03198682e69dc1c2341006e6085a9064108db1f93c64928bf5da07943a21", "generation_seconds_batch": 14.843053326942027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7158743739128113, "target_z": 0.9531250268696181, "ce": 6.0305562019348145, "genuineness": 4.15588903427124, "identity": 0.7005855441093445, "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_Pride/1159cc35ac2b79d2f089402bcd2ee81bbe1117265934eb16e57a6721f4440655.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "124c1f7e821523cb284e809800010c8021b2522e015fe54ec62c18999f097cb9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fd8aa876bf88bb86481fd2020fbf8cbe5f37e90cbaab3e39b28a310dbde7e0db", "generation_seconds_batch": 18.427111599012278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5574636459350586, "target_z": 0.648437486565191, "ce": 6.133810997009277, "genuineness": 4.168440818786621, "identity": 0.8096963167190552, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/124c1f7e821523cb284e809800010c8021b2522e015fe54ec62c18999f097cb9.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "129dac217212bf9a46f5d360116821f6b9906a15bdc2148f94a13ebe4f0e047f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0156f51b797e7ce6adfd5f01c3203671e7f9a63256369e36e96f52bfbe98f94c", "generation_seconds_batch": 21.245069639990106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6346380710601807, "target_z": 0.7968749444694558, "ce": 6.197352409362793, "genuineness": 4.068024158477783, "identity": 0.654475212097168, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/129dac217212bf9a46f5d360116821f6b9906a15bdc2148f94a13ebe4f0e047f.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "2ab882563e88e1b7cd1a9aa6134e0c0b7a368885e34a39c6759060632e7dc7a5", "generation_seconds_batch": 14.745023909024894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.935212254524231, "target_z": 1.374999985669537, "ce": 6.324435234069824, "genuineness": 4.193545341491699, "identity": 0.8141734600067139, "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_Pride/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "12bdf22f3346814b514ea892377566488d80df52b310604a4108c30744d58dea", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c98b67e6bbe2520df1bbded0d82d676dc44763cfbbec2e205d2f5f5d9419df47", "generation_seconds_batch": 19.339755540015176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.689915418624878, "target_z": 4.749999885356296, "ce": 6.38003396987915, "genuineness": 4.111956596374512, "identity": 0.5323435068130493, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/12bdf22f3346814b514ea892377566488d80df52b310604a4108c30744d58dea.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "12e83aaafa2b72c6e1f2803d9f5dbb8fd2ee80ba6a7ed6aca67efa041535acfd", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "aaf659dc1a4428e4543f244128512656ba6e934b6e61fa354fdeb72375a18e2f", "generation_seconds_batch": 19.460940657998435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.567618191242218, "target_z": 0.6679687611956742, "ce": 6.23706579208374, "genuineness": 4.243753433227539, "identity": 0.4793092906475067, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/12e83aaafa2b72c6e1f2803d9f5dbb8fd2ee80ba6a7ed6aca67efa041535acfd.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "12f015af948f5251306d784720392d69a8c27982ae9e5c4d045c95613972734c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "50fd840f4aaca7b0dc226594d15cd223c86258062a5dd09f537862ea521f0dc6", "generation_seconds_batch": 21.260343733010814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4632480144500732, "target_z": 2.390625120017628, "ce": 6.340320587158203, "genuineness": 3.9299514293670654, "identity": 0.5051981806755066, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/12f015af948f5251306d784720392d69a8c27982ae9e5c4d045c95613972734c.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "1358ae046d51f75387bb968293eef8f49a6583eb3eee6f299bcf349b577225f0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ef095a02c402e77dd990f2ea8d97f15d4efe1eba435b5a0a8b05e495de4d3894", "generation_seconds_batch": 18.434210898936726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0245721340179443, "target_z": 1.546874973130382, "ce": 6.316492557525635, "genuineness": 3.9927117824554443, "identity": 0.39919185638427734, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1358ae046d51f75387bb968293eef8f49a6583eb3eee6f299bcf349b577225f0.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": "13e1bad9ef1f61a0ddb52a49697f91debf316a63a9c6a51cd8215e2f021d5ea2", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "22c370b863f92569d17b413b29b93233460c8ba97df83ecec85908314eb21894", "generation_seconds_batch": 20.069005643948913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0976847410202026, "target_z": 1.6874999211824535, "ce": 6.213237762451172, "genuineness": 4.18099308013916, "identity": 0.6603633165359497, "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_Pride/13e1bad9ef1f61a0ddb52a49697f91debf316a63a9c6a51cd8215e2f021d5ea2.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "1464bd6ca4cf44f93bfd196f8379e4732c31bb6fcd7d46a4383a9afe312a9148", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ae2c646f6af77f2c45a8c5f5f931d2ff4b0f996b4448be4f20d53c4b14f187c2", "generation_seconds_batch": 22.64016802003607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.430753469467163, "target_z": 2.328125041200081, "ce": 6.197352409362793, "genuineness": 4.193545341491699, "identity": 0.4723191559314728, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1464bd6ca4cf44f93bfd196f8379e4732c31bb6fcd7d46a4383a9afe312a9148.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "1468811660710cf0324f86c798406327f7445f80928e654dfbb7b4bae77e8336", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1c402bb9378e313736150427adc0a04d599d2b5e839ae43be79fb58e5059c39b", "generation_seconds_batch": 20.806108572985977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4843510389328003, "target_z": 0.5078125385131194, "ce": 6.054384231567383, "genuineness": 4.193545341491699, "identity": 0.7721489667892456, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1468811660710cf0324f86c798406327f7445f80928e654dfbb7b4bae77e8336.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "148c58dbdf18de15755f135ab21e6e9e0082d1fa6bc2ad9b5a91251db6eeb842", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "bce62e8500edb1329309866ccd7624e5aca7d374833296a717d2d117943cf365", "generation_seconds_batch": 14.61174995393958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.22360098361969, "target_z": 1.9296874973130382, "ce": 6.078212261199951, "genuineness": 4.250029563903809, "identity": 0.5636062026023865, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo", "wer": 0.17647058823529413, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/148c58dbdf18de15755f135ab21e6e9e0082d1fa6bc2ad9b5a91251db6eeb842.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "15136bc2157a19212ec156971d37313dd04134f8c999d0615d26771117496086", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d7084b9da2c54655429369aaba48eb2c63fcf0f576bf10e06df72ada370bf0d4", "generation_seconds_batch": 19.653450220939703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1017465591430664, "target_z": 1.6953124310346468, "ce": 6.284721851348877, "genuineness": 4.469690799713135, "identity": 0.6093825101852417, "hypothesis": "Die Tür 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_Pride/15136bc2157a19212ec156971d37313dd04134f8c999d0615d26771117496086.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "153c9c34fd291b25996e89d63ffced2c678a216b7a415a79685a521512b23ad7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "32b7269c6a18911b3d12f2767d30b55e9d88bfecfc0edff3e19e1d08d7848ad1", "generation_seconds_batch": 15.021931760013103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1342411041259766, "target_z": 1.7578125098521933, "ce": 6.141753673553467, "genuineness": 4.143336772918701, "identity": 0.6939672827720642, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/153c9c34fd291b25996e89d63ffced2c678a216b7a415a79685a521512b23ad7.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "4986ee83e87daed1df1cf7a3e3a3a656ac4367374a10a933065849c5d2fdb7db", "generation_seconds_batch": 14.280613871989772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5209073424339294, "target_z": 0.5781250125391552, "ce": 6.332377910614014, "genuineness": 4.13078498840332, "identity": 0.4123173952102661, "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_Pride/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "1585681abfd6e12327d5b02bf36af1def86af10dfc0fae33917020584336af3b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8c59232f0d8b3f2459b8407967ec41fafdaec049e5c04f96f3f58ed22d90fb02", "generation_seconds_batch": 14.951749125029892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.048943042755127, "target_z": 1.5937500322435418, "ce": 6.0305562019348145, "genuineness": 4.545003414154053, "identity": 0.4252338409423828, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1585681abfd6e12327d5b02bf36af1def86af10dfc0fae33917020584336af3b.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "15b5b034939bcb98454ffa83e219eec8f90e3a23a95aaf7930dff2e67eddc2a0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5bd4a537ff0c79c0c929e0e4bdc48864380bf6ec61561ae110c34b08dd88c10c", "generation_seconds_batch": 13.910683244932443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9270886182785034, "target_z": 1.3593749659651504, "ce": 6.300607204437256, "genuineness": 4.099404335021973, "identity": 0.3700762391090393, "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_Pride/15b5b034939bcb98454ffa83e219eec8f90e3a23a95aaf7930dff2e67eddc2a0.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "15bdf9f5d76dad05af97e1790fac415b3d39c41c57876196883b4b5108e297dd", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "32c46ed5237cf7ae74a4352a856a4181bde9a2b0568c02a217eec7ad4527a11b", "generation_seconds_batch": 18.594208437018096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8661614060401917, "target_z": 1.2421874328259548, "ce": 6.260893821716309, "genuineness": 3.9299514293670654, "identity": 0.37557870149612427, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/15bdf9f5d76dad05af97e1790fac415b3d39c41c57876196883b4b5108e297dd.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": "15f65e07efc82eaf3fe230a155eeac9e275e15112ee1e801292b17d87f50e830", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "05cd653f7cb86bea806a14f738878c6dc70f860a92455b1a7814e5e39a162e10", "generation_seconds_batch": 13.800161899067461, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6744623184204102, "target_z": 2.796875173756864, "ce": 6.205295085906982, "genuineness": 3.7165660858154297, "identity": 0.527583122253418, "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_Pride/15f65e07efc82eaf3fe230a155eeac9e275e15112ee1e801292b17d87f50e830.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "1605ed048b9b2c0fed5bb00b9a5f39b0ce763274b1ca201bc2009362413d28ca", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ee1995df5d26fb18f4f867016f345d54b61d1e917d801d932cc2bfe225ee00ce", "generation_seconds_batch": 19.602618237026036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7077507376670837, "target_z": 0.9375000071652315, "ce": 6.252951145172119, "genuineness": 4.7458367347717285, "identity": 0.4980278015136719, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1605ed048b9b2c0fed5bb00b9a5f39b0ce763274b1ca201bc2009362413d28ca.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": "16733b4bfb4d0581bb51b6dd677f3cbc64fa7b92f28e23e9d9f30b50cdfa887d", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b629b7f2e532411e7d27e0c706bf90c4086e03e528d7ad8b7d7f1751c2c00cda", "generation_seconds_batch": 15.954988455981947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5534018278121948, "target_z": 0.6406249767129977, "ce": 6.205295085906982, "genuineness": 4.394378662109375, "identity": 0.6583096981048584, "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_Pride/16733b4bfb4d0581bb51b6dd677f3cbc64fa7b92f28e23e9d9f30b50cdfa887d.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "17537971ec64a9d397f7e366770820562d5de2b758eda733d59d092da6bf6661", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a5d708f7fe893b8d991a66c099373cd60e32901ca12d76b133b3134daed82aac", "generation_seconds_batch": 19.003130811965093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36960479617118835, "target_z": 0.2871093644760662, "ce": 6.181467056274414, "genuineness": 4.281409740447998, "identity": 0.6014003753662109, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/17537971ec64a9d397f7e366770820562d5de2b758eda733d59d092da6bf6661.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "1762ff9b97b92d5518c520d5ead48564d8c104c24df1eec6a2ef60480f8cd423", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "91d633527287c32b6c9813e164cd0d9fb244a653846216a0e888acc8338dfafc", "generation_seconds_batch": 20.691561237093993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9433358907699585, "target_z": 1.3906250053739235, "ce": 6.086154937744141, "genuineness": 3.923675537109375, "identity": 0.4902963638305664, "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_Pride/1762ff9b97b92d5518c520d5ead48564d8c104c24df1eec6a2ef60480f8cd423.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": "1802a222976a31507ec573ea4fe644cbcb50395d74a259a0eabd8a56e624c2d7", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b111aa0dba129c538fec77cc95e2963f89df2f8d23ae6d333906c8b610eb5798", "generation_seconds_batch": 16.2076419449877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.70368891954422, "target_z": 0.9296874973130382, "ce": 6.316492557525635, "genuineness": 4.281409740447998, "identity": 0.6398717164993286, "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_Pride/1802a222976a31507ec573ea4fe644cbcb50395d74a259a0eabd8a56e624c2d7.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "183b239c4957bcaa9b9ac30440186e00a9c4b20557efda2aa6d5ccdc07ac3b09", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6f795325c0142c0726ce218a9b53692c26a04b028bb607636b32daaac8e546c3", "generation_seconds_batch": 14.999106334056705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3649704456329346, "target_z": 4.125000014330463, "ce": 6.395919322967529, "genuineness": 4.174716949462891, "identity": 0.49521100521087646, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/183b239c4957bcaa9b9ac30440186e00a9c4b20557efda2aa6d5ccdc07ac3b09.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "187955ac43358e7824bee9055c3db029d0e6333a2bd4bbbdcdae90a7e46d29b6", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "7333c4cb8981eb6e128139257d0c3e975df926137d9b1ee036387885e2db46ad", "generation_seconds_batch": 13.861822366947308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0002013444900513, "target_z": 1.50000014330463, "ce": 5.772419452667236, "genuineness": 3.8922953605651855, "identity": 0.5827285647392273, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/187955ac43358e7824bee9055c3db029d0e6333a2bd4bbbdcdae90a7e46d29b6.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "18dbcaaa4360aed97da9cc1592365c1bfb0d50c37a7a4f8f9790b81e16bfce68", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b590e8301afe7ffc4098b409797e4db15b2a62e8dcad22ffaf6997364883d74d", "generation_seconds_batch": 18.61781287100166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6021435856819153, "target_z": 0.7343749802956133, "ce": 6.292664527893066, "genuineness": 4.507347106933594, "identity": 0.6140725016593933, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/18dbcaaa4360aed97da9cc1592365c1bfb0d50c37a7a4f8f9790b81e16bfce68.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "19886327d3aaa31419e9e1ecc8944c5e3484f6c94be5aeeaf963e8994e48dea5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f01d697cfb0b46c2d054b115b66f31560c38e3decd1eba6fa4e4043ae78dd50e", "generation_seconds_batch": 14.783225922030397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3487231731414795, "target_z": 4.09374997492169, "ce": 6.229123115539551, "genuineness": 3.8044304847717285, "identity": 0.3098093271255493, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/19886327d3aaa31419e9e1ecc8944c5e3484f6c94be5aeeaf963e8994e48dea5.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "19a59cd44aa2f942a50becaf400dc68d46cdbe1d04732ff93d10d9a156bf9796", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "197798243f7d2f1fcaf4a9117aae6133014d66e2f71ff88bc95928bc396960d0", "generation_seconds_batch": 14.951749125029892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0733139514923096, "target_z": 1.6406250913567015, "ce": 6.332377910614014, "genuineness": 4.394378662109375, "identity": 0.5574470162391663, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/19a59cd44aa2f942a50becaf400dc68d46cdbe1d04732ff93d10d9a156bf9796.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "19cf531ccdbb93f80f295df7b593f4569035b992bb0da74fbab586dfbc3eda32", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f960043d154e06c90f2f91bdf9aae58a419fa6f93ecae09d3d57d3a979e7ac5a", "generation_seconds_batch": 21.76221097598318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.218745231628418, "target_z": 3.84375011822632, "ce": 6.213237762451172, "genuineness": 4.306513786315918, "identity": 0.4822614789009094, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/19cf531ccdbb93f80f295df7b593f4569035b992bb0da74fbab586dfbc3eda32.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "1b26900924b92ee338ff6bd08157dad2f390d9cc9af41973da42473bccba3d51", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00aaa3054dcd611bcc89670d2f76fcf8ef0aab06c3d82ae966430c7febf6bd1d", "generation_seconds_batch": 14.079049113905057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6338441371917725, "target_z": 2.7187500752349307, "ce": 6.09409761428833, "genuineness": 3.760498285293579, "identity": 0.2656167149543762, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1b26900924b92ee338ff6bd08157dad2f390d9cc9af41973da42473bccba3d51.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "1b4e7bbdbbc5212a936effb011ae38395c85b3b96513dfbeb0b8452c73e176a8", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c15f46363418b70727ab49d04d8a620ca458f609db4e692efe571ee3bbd927a2", "generation_seconds_batch": 18.574609696050175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1545501947402954, "target_z": 1.79687505911316, "ce": 6.1894097328186035, "genuineness": 3.9173994064331055, "identity": 0.18657708168029785, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1b4e7bbdbbc5212a936effb011ae38395c85b3b96513dfbeb0b8452c73e176a8.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "1be1d649ab39e4d40c0f1648a24872cc91273e72993c68845653a635e2aaa335", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "2fb5d80ae469e34ccf07df4e697243dcd008c27ae94f3d4499ace4885e836360", "generation_seconds_batch": 20.69968763110228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9270886182785034, "target_z": 1.3593749659651504, "ce": 6.284721851348877, "genuineness": 4.042920112609863, "identity": 0.5020931959152222, "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_Pride/1be1d649ab39e4d40c0f1648a24872cc91273e72993c68845653a635e2aaa335.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "1c166d112cb360c5011d56f0e612cbef62fb20a155b18c05d28f81db944604be", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4bd39012f172eea551a9b160e0c64df631d4216fcef4530f9f144815efd0a96f", "generation_seconds_batch": 14.210173981031403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6285454034805298, "target_z": 0.7851562943348699, "ce": 6.046441555023193, "genuineness": 4.331617832183838, "identity": 0.6545742750167847, "hypothesis": "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_Pride/1c166d112cb360c5011d56f0e612cbef62fb20a155b18c05d28f81db944604be.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "1c325e4014e2aeabcbc0591ceb72759274cffd59df137ce24b3a2c18d7814110", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4cf367fefe446c63cab3d53afd008d3b2459bf1565672fc502c04c76706f3c87", "generation_seconds_batch": 22.167867842013948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8986559510231018, "target_z": 1.3046875116435013, "ce": 6.125868320465088, "genuineness": 3.911123275756836, "identity": 0.5506068468093872, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1c325e4014e2aeabcbc0591ceb72759274cffd59df137ce24b3a2c18d7814110.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": "1c471b3a61d1bbf44cd74edb2ed17bf6153d1f2cb6032662eb51d1a5f2db3df8", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b934b55721cf4d2ba9bc4a5d795acbca7228e1c347be0fc15406651079997734", "generation_seconds_batch": 14.911178280017339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6041744947433472, "target_z": 0.7382812352217101, "ce": 6.149696350097656, "genuineness": 4.061748504638672, "identity": 0.6523164510726929, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd...", "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_Pride/1c471b3a61d1bbf44cd74edb2ed17bf6153d1f2cb6032662eb51d1a5f2db3df8.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "1c8032f4bf3eaa0775c9307c28475acfc3bc7328bc4fd1b9fbac327cbe9488cf", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2c3d8af16db3858225ca733e929ce6184099865d96ab2038a368180bc0ef22c1", "generation_seconds_batch": 21.742597217089497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0042630434036255, "target_z": 1.5078124238694153, "ce": 6.292664527893066, "genuineness": 4.193545341491699, "identity": 0.768687903881073, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1c8032f4bf3eaa0775c9307c28475acfc3bc7328bc4fd1b9fbac327cbe9488cf.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": "1cabbb1369cf4dd3dd6092b630bab998827c1d4ec343ff7970632bf356e9f65a", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce4e50b810aa52ef1a764e7050a1d76ce603ca4f16c53d8facc67a065353dca2", "generation_seconds_batch": 18.39796023501549, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7963166236877441, "target_z": 3.031250010747847, "ce": 6.324435234069824, "genuineness": 4.15588903427124, "identity": 0.5438665747642517, "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_Pride/1cabbb1369cf4dd3dd6092b630bab998827c1d4ec343ff7970632bf356e9f65a.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "1caff2ac39bdc4417757ceea0d6fdfa7584f05bf1b5898d202a82228de543932", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a9e38791223b20dd277850fe6e28ca4c3e61c7b29ff547ba2abf10ac7f0c1daa", "generation_seconds_batch": 18.546944680041634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0887670516967773, "target_z": 3.593749802956134, "ce": 6.332377910614014, "genuineness": 4.124508857727051, "identity": 0.6139106750488281, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1caff2ac39bdc4417757ceea0d6fdfa7584f05bf1b5898d202a82228de543932.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "1cea202da68c1a33615d9e201386700965b90b4a68a482d59fb5b47dc9911b77", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5c5e76a92219b8d20d0c409156e04942e8384acb8d059795effc3fde96b6deac", "generation_seconds_batch": 21.34765262308065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8255432844161987, "target_z": 1.1640624489477256, "ce": 6.133810997009277, "genuineness": 4.118232727050781, "identity": 0.616138219833374, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1cea202da68c1a33615d9e201386700965b90b4a68a482d59fb5b47dc9911b77.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "1ceb94c3ef10a0a1ce51f16c7fa13da07f68401cf2ea1cdbf5f10ac529c4762d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "aafd9b794074d026fbe9082dc5651db7bcc9fddf90f5ea00691b5214392f8e0a", "generation_seconds_batch": 23.682215058943257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5696491003036499, "target_z": 0.6718750161217709, "ce": 6.038498878479004, "genuineness": 4.425758361816406, "identity": 0.46955299377441406, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1ceb94c3ef10a0a1ce51f16c7fa13da07f68401cf2ea1cdbf5f10ac529c4762d.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "1cfc78097244b8ae3751b797ba12ea0fbc9e513ad2d1e6eb4202bbac0cf88691", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "76016789bec44768a3b83b99aa61b138a50fb3b4ef156e160a77a6f91176321f", "generation_seconds_batch": 17.629598545958288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1504883766174316, "target_z": 1.7890625492609666, "ce": 6.284721851348877, "genuineness": 3.9425034523010254, "identity": 0.23897668719291687, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1cfc78097244b8ae3751b797ba12ea0fbc9e513ad2d1e6eb4202bbac0cf88691.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "1d13ecc94eb971c75deefd24fe0b6d15df469a1af982d93a17df00d236ece5cd", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "52d7b964727d853a52758c6864107de1b4cd50db5aebfb0d2575a2ebf032983f", "generation_seconds_batch": 19.931992057012394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6833798289299011, "target_z": 0.8906249480520716, "ce": 6.165581703186035, "genuineness": 4.3881025314331055, "identity": 0.3861006200313568, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay de aquí.", "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_Pride/1d13ecc94eb971c75deefd24fe0b6d15df469a1af982d93a17df00d236ece5cd.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "597ba2c099df6e1b607b22e8a63f957bf20bf5bc8f69a893bcfdbbd855cd65c7", "generation_seconds_batch": 14.60745631204918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4226298332214355, "target_z": 2.3125000214956946, "ce": 6.133810997009277, "genuineness": 4.344170093536377, "identity": 0.5774794816970825, "hypothesis": "Escribí el número en el sobre, léelelo bien, y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.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": "1d6903357e66473fa19fb9e8861c8840ab589cdc4c80eea1426c8a88335c6d43", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1b2b05db045876106bb9cafd072db788dda6dfec4b7b96c4a58a320b78bb7f69", "generation_seconds_batch": 14.681333899032325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6094732284545898, "target_z": 2.671875016121771, "ce": 6.109982967376709, "genuineness": 4.231201171875, "identity": 0.7440388202667236, "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_Pride/1d6903357e66473fa19fb9e8861c8840ab589cdc4c80eea1426c8a88335c6d43.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "180fad9bd7b92de472337fa13f1e3405fd5dc760667d60be301f84874ddbc6b7", "generation_seconds_batch": 16.504361557075754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2051013708114624, "target_z": -0.02929688328479892, "ce": 6.356205940246582, "genuineness": 4.557555198669434, "identity": 0.4194124937057495, "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_Pride/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "1d881b60382cddd774624bd474f0a16d7e593817be869c5c04bf4827be804e13", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ed3e10c3b03b9734977c77808eff5fa1d718a1a62ef0f4f1637b3ea1f906aac", "generation_seconds_batch": 22.745843692915514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6996271014213562, "target_z": 0.9218749874608448, "ce": 6.046441555023193, "genuineness": 4.243753433227539, "identity": 0.6885571479797363, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1d881b60382cddd774624bd474f0a16d7e593817be869c5c04bf4827be804e13.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": "1e57d82ed338dda98af1bf47abd62dbdcc9ee71161a07b078c23fd85dc8dc73b", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cf334a51e5b98d45ec5265a02d405ed83290c09df69fe1fdf759225f4fd0fd25", "generation_seconds_batch": 22.473764788010158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.528236985206604, "target_z": 2.5156250483653126, "ce": 6.38797664642334, "genuineness": 4.093128204345703, "identity": 0.4994414448738098, "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_Pride/1e57d82ed338dda98af1bf47abd62dbdcc9ee71161a07b078c23fd85dc8dc73b.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "1e7d599c66575e116786f9fe6dce21cfabe5b3b9e97bb2426eefe6efb8c71015", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2388d9f9c7a562059899464864cab2245aec77df8b45992dbc57f60984cbc28f", "generation_seconds_batch": 20.772530908929184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8011724352836609, "target_z": 1.1171875044782698, "ce": 6.054384231567383, "genuineness": 4.3881025314331055, "identity": 0.6571669578552246, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1e7d599c66575e116786f9fe6dce21cfabe5b3b9e97bb2426eefe6efb8c71015.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "1e83feca764775d9369d8671460ce2ac70b0e426a49fb06860e4c2d60989a3e0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d07fd776aeb1173a14fc35b2cf5153fb8067135bd41a6d19bc1049baf36f3768", "generation_seconds_batch": 22.032132284948602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.414506196975708, "target_z": 2.296875001791308, "ce": 6.173524379730225, "genuineness": 4.055472373962402, "identity": 0.6455375552177429, "hypothesis": "De deur 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_Pride/1e83feca764775d9369d8671460ce2ac70b0e426a49fb06860e4c2d60989a3e0.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "1e925ce2e36ed56540789b0461fffd3310f7fc62d0dd6752de48d93115d6ef85", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4efa4c80564bea9312f9e0d003b6310673736901325c3698b2ad5be2d539ee08", "generation_seconds_batch": 18.546944680041634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5363606214523315, "target_z": 2.531250068069699, "ce": 6.229123115539551, "genuineness": 4.287685871124268, "identity": 0.36791008710861206, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1e925ce2e36ed56540789b0461fffd3310f7fc62d0dd6752de48d93115d6ef85.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5e549d25abec40784e21824ea99a673ec2be3eaad4d870882d80374723d7b33b", "generation_seconds_batch": 14.60745631204918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0083248615264893, "target_z": 1.5156249337216086, "ce": 6.260893821716309, "genuineness": 4.344170093536377, "identity": 0.6393707990646362, "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "1f36620498fc49c928ac8d3aed7b27f840cd6229aea159ffc9190a3b4cb4e345", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "03b0b81203467b0025e01b9ab8dafa725a781fd0d4ff2d722b6a563119609e34", "generation_seconds_batch": 19.593828320037574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3738881349563599, "target_z": 2.218750132556783, "ce": 6.125868320465088, "genuineness": 4.105680465698242, "identity": 0.5389441251754761, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1f36620498fc49c928ac8d3aed7b27f840cd6229aea159ffc9190a3b4cb4e345.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": "1f3a69f4f425036d5059d71dd90e745a8ec1e53476f2c3e714c807d61a4a9402", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96c611367ea555b5a2d747012c89d5e06c78386ee2d90406cc06321f2d7b13aa", "generation_seconds_batch": 13.864651568001136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.951459527015686, "target_z": 1.4062500250783103, "ce": 6.292664527893066, "genuineness": 4.118232727050781, "identity": 0.3214007616043091, "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_Pride/1f3a69f4f425036d5059d71dd90e745a8ec1e53476f2c3e714c807d61a4a9402.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "1f4ce7600075cca5d5857a9fb31af6bec9dca6222dc0eed720a3ccb508f834b4", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5e23e6a86aa4826c7e61c8aa67aae589c2fca09da82dac86f6a669f262555249", "generation_seconds_batch": 15.548954220954329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4396710693836212, "target_z": 0.4218749874608449, "ce": 6.324435234069824, "genuineness": 4.2249250411987305, "identity": 0.45145708322525024, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1f4ce7600075cca5d5857a9fb31af6bec9dca6222dc0eed720a3ccb508f834b4.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "1f563ad497bf4e07e56b4a64e9ca71ee4b36747627c3c56e0a81d2eaaebbb873", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bf3d742c290ec8125a098917860b1af3b606fdca9994f2f0d0d018d39f4a0a7d", "generation_seconds_batch": 19.783498172997497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.738657236099243, "target_z": 4.843750003582616, "ce": 5.824047088623047, "genuineness": 4.055472373962402, "identity": 0.41213953495025635, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1f563ad497bf4e07e56b4a64e9ca71ee4b36747627c3c56e0a81d2eaaebbb873.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "1fdc75f40874afc2b3081e177174c27370201fca84975c29b453ef296f695faf", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "baaf276698265a4eb6e9128c1a7c1eefd1b9eea1c053556464d3efd2a2d7bf8e", "generation_seconds_batch": 13.803774839034304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.012386679649353, "target_z": 1.5234374435738018, "ce": 5.982900142669678, "genuineness": 3.8044304847717285, "identity": 0.6484451293945312, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/1fdc75f40874afc2b3081e177174c27370201fca84975c29b453ef296f695faf.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "20cfa220679f5099f8ed6489c707c53dfb8b3173d9ea9afc23d7f0b167907147", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e1f15619045d269b6afe3a63bbfe1050b52e1715677ffc8777ae85cef41ddb10", "generation_seconds_batch": 18.54090722789988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9473977088928223, "target_z": 1.398437515226117, "ce": 6.054384231567383, "genuineness": 3.9550557136535645, "identity": 0.652624249458313, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/20cfa220679f5099f8ed6489c707c53dfb8b3173d9ea9afc23d7f0b167907147.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "213ec806c6909fc1bb0e2bc7372a4e2fc98e08d565e21460f52a1501d8f68e53", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "54de998c20fe7f04f5b3a681a3bd7eeba4e040f9062107773f75de32bd5ab433", "generation_seconds_batch": 13.780542536987923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.992077648639679, "target_z": 1.4843750089565393, "ce": 5.974957466125488, "genuineness": 3.8420867919921875, "identity": 0.4439541697502136, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/213ec806c6909fc1bb0e2bc7372a4e2fc98e08d565e21460f52a1501d8f68e53.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "218277b28dd42bd555e6261c83013cf6fd4539eab12509e2a7ff9f0d1447fa62", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cf0874521a6f4d5d18fa81e702a40165688c1a9560a8fdc98f91186c7a7fa21e", "generation_seconds_batch": 20.360231151920743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.764616072177887, "target_z": 1.04687491580853, "ce": 6.3641486167907715, "genuineness": 4.143336772918701, "identity": 0.3127610385417938, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/218277b28dd42bd555e6261c83013cf6fd4539eab12509e2a7ff9f0d1447fa62.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "21f097b17d6db5060500a7531348a2950726dd5e7a8629087f20464493ddaeb7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "194dc257988b4c76ce1792cfe0d51c9730d2286e5a9506e8eb3c95af951869e6", "generation_seconds_batch": 14.907041014055721, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.567618191242218, "target_z": 0.6679687611956742, "ce": 6.372091293334961, "genuineness": 4.68307638168335, "identity": 0.8656908869743347, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/21f097b17d6db5060500a7531348a2950726dd5e7a8629087f20464493ddaeb7.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": "2202502f3767471dd6ec5ee061b2580e1881795d4410137fe714bfe68b49da0d", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Escribí el número en el sobre.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f99b2f1428dabcf8ad7db2c92cd689ef0413a1f124c39970db23376900063e96", "generation_seconds_batch": 22.280046370928176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7638221979141235, "target_z": 2.9687501612177085, "ce": 6.1020402908325195, "genuineness": 4.20609712600708, "identity": 0.6761348247528076, "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un nombre.", "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_Pride/2202502f3767471dd6ec5ee061b2580e1881795d4410137fe714bfe68b49da0d.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": "2259f5be7787f9367f93a8e8fc1da0bbe457a0fa717ea6e706641e5717de99ff", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "28b07b49fd2668e8134273279ca4d41cf8978734c26774f620c3e182ee97bd34", "generation_seconds_batch": 14.82747878599912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8905323147773743, "target_z": 1.2890624919391145, "ce": 6.181467056274414, "genuineness": 3.8797430992126465, "identity": 0.7301088571548462, "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_Pride/2259f5be7787f9367f93a8e8fc1da0bbe457a0fa717ea6e706641e5717de99ff.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "22beead74f17ee6335e703249c8c4c9483bc3819907d3b5b7b7d52f75a462452", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d4863deaf4b63b3c387b1adada6e7eb2fa8b3e95408cd0f1d398c256b574101a", "generation_seconds_batch": 18.58470865606796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.771945834159851, "target_z": 2.9843751809220955, "ce": 6.1894097328186035, "genuineness": 4.268857479095459, "identity": 0.5374521017074585, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/22beead74f17ee6335e703249c8c4c9483bc3819907d3b5b7b7d52f75a462452.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": "22cbca5c0e9b4eab5460864663ac3b26d4269c212f5d2c0b11a8adfcd20170bf", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d814e917596ccf7c424c04ba10a76c4e39799ceed1aba446dcdcba33356685de", "generation_seconds_batch": 15.111752734985203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6082363128662109, "target_z": 0.7460937450739034, "ce": 6.229123115539551, "genuineness": 4.080576419830322, "identity": 0.4736967086791992, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/22cbca5c0e9b4eab5460864663ac3b26d4269c212f5d2c0b11a8adfcd20170bf.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "232d048dd5b337769237fa00c56897959967e4ca8800f7e541dea34b4d7e2690", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "64af0829936ab810f3d6f04763b791768c653953610e3066b83bb734f75fd157", "generation_seconds_batch": 19.12807909399271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1375088691711426, "target_z": 3.6874999211824533, "ce": 6.316492557525635, "genuineness": 4.13078498840332, "identity": 0.3097681999206543, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/232d048dd5b337769237fa00c56897959967e4ca8800f7e541dea34b4d7e2690.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "23d9bb53709307c7b70888519495168008eee060af7b80a5fcb662930078e286", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b916a821a96012c7746817848b75f065645c16fa5b585afb6cdac8e956e965a2", "generation_seconds_batch": 20.485461720032617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8702232241630554, "target_z": 1.249999942678148, "ce": 6.078212261199951, "genuineness": 4.093128204345703, "identity": 0.717681884765625, "hypothesis": "J'ai trouvé la 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_Pride/23d9bb53709307c7b70888519495168008eee060af7b80a5fcb662930078e286.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "246dda0771a718b32f7c4ddfbd3058ab10e049ec0e1739e88c117b299b03dcd1", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "975bbb9a6ff1ae342c6dd235cc5c451d4d9754978519b0b88a0aa7070e9d46b1", "generation_seconds_batch": 18.997785553103313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6249263286590576, "target_z": 4.624999727721203, "ce": 6.0146708488464355, "genuineness": 3.9801597595214844, "identity": 0.5181444883346558, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás llorando.", "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_Pride/246dda0771a718b32f7c4ddfbd3058ab10e049ec0e1739e88c117b299b03dcd1.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "2486c494f1273dacf52abc2260672a61dcd1c9fbf5b839e33ef916820617600c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2215974bb21f4f1caa6f72b21e347d24846875a67598d8fdba37381546d7d489", "generation_seconds_batch": 18.961174075026065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9311504364013672, "target_z": 1.3671874758173437, "ce": 6.197352409362793, "genuineness": 4.256305694580078, "identity": 0.710010826587677, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/2486c494f1273dacf52abc2260672a61dcd1c9fbf5b839e33ef916820617600c.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "24ef58794ccd3cb344a3fdfc4a47f59ec042931bf5e5faac153c5f561a090ab2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9b1881c6d7f80bf06b69db9de42cc7278fe6000300df06c99514b3b73cdc3b22", "generation_seconds_batch": 14.999106334056705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9181710481643677, "target_z": 3.2656250770262387, "ce": 6.435632705688477, "genuineness": 4.005263805389404, "identity": 0.47305068373680115, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/24ef58794ccd3cb344a3fdfc4a47f59ec042931bf5e5faac153c5f561a090ab2.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "24fd8a36db5f2d2cd9bd1b09f78759ee2ba041178be5b6c4fb3493cab7b6353c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6eae154c8dc87305ca975cbcd4138dc7e9b158e51da054fd5b33bb7b2b41b824", "generation_seconds_batch": 23.360744339996018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.292651891708374, "target_z": 2.0625001648003245, "ce": 6.125868320465088, "genuineness": 3.9299514293670654, "identity": 0.4073534309864044, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/24fd8a36db5f2d2cd9bd1b09f78759ee2ba041178be5b6c4fb3493cab7b6353c.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "25251af3fb0687dcea39217914610a241cd2346e5d93cd395094b43a10828a6b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "357fa315b0226d7d2217c506dfe4bdf8af4667a7bdc2eaeb6174bef0923ec9e9", "generation_seconds_batch": 14.079049113905057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1301792860031128, "target_z": 1.75, "ce": 6.117925643920898, "genuineness": 3.7040140628814697, "identity": 0.34765806794166565, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/25251af3fb0687dcea39217914610a241cd2346e5d93cd395094b43a10828a6b.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "25517fe68c6c8ced99bce70ece2edeeb0a78ef2b4162e6aec48731c14c06bc1c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "102c845344e94231d86538c6bd6f32901f828b15ac67921a8ab48d444cecd1e4", "generation_seconds_batch": 19.22525927599054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5432472825050354, "target_z": 0.6210937020825144, "ce": 6.356205940246582, "genuineness": 4.256305694580078, "identity": 0.35402020812034607, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/25517fe68c6c8ced99bce70ece2edeeb0a78ef2b4162e6aec48731c14c06bc1c.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "25db688c5f906584f55e9bdfa45f73414c537690615bdd7ff4f4cb0d40a2450d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ebeff861464b65a9e561e127bc58463ef659c69ab0708b56f8ac077bbbb2196f", "generation_seconds_batch": 19.475732991006225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0473549365997314, "target_z": 5.4374998351996755, "ce": 6.268836498260498, "genuineness": 3.8797430992126465, "identity": 0.44262006878852844, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam.", "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_Pride/25db688c5f906584f55e9bdfa45f73414c537690615bdd7ff4f4cb0d40a2450d.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "267b34c0164508e9459933a8ce31f3c0bfbb146ab96c3055812a49b2d7b92e17", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "376f153f1997a92526ab83b38e16f5c8c186e70c9b4842aa01e19d859ed0d73f", "generation_seconds_batch": 18.64211778191384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0854994058609009, "target_z": 1.6640626209132816, "ce": 5.601652145385742, "genuineness": 4.011539936065674, "identity": 0.4165123701095581, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/267b34c0164508e9459933a8ce31f3c0bfbb146ab96c3055812a49b2d7b92e17.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "956192348bdb19284a791ac94b05f80277f84c379c7546099d18cafd92f65c75", "generation_seconds_batch": 14.189587521017529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.472165584564209, "target_z": 0.4843750089565394, "ce": 6.4912309646606445, "genuineness": 4.300237655639648, "identity": 0.21396680176258087, "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_Pride/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "271c99f0fd0b9babe46f2eb54b8a4ad130c6890ccb94b61f1fd96d1b23e0c01c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5a29c19e13956a12390125b6223f89b2915300f7a48f4e37051b629875a2642", "generation_seconds_batch": 18.43912618502509, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0245721340179443, "target_z": 1.546874973130382, "ce": 6.205295085906982, "genuineness": 4.099404335021973, "identity": 0.2143280804157257, "hypothesis": "The door is still open. Hi. 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_Pride/271c99f0fd0b9babe46f2eb54b8a4ad130c6890ccb94b61f1fd96d1b23e0c01c.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "2743fd453df86b7548aae7410d092096595d8ffb249734467185863ad2984053", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "76169e56a5dda0c3335bef01e7897c39f08096afa37a997691875f3cea7d9eaf", "generation_seconds_batch": 18.659525066032074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3324759006500244, "target_z": 4.062499935512917, "ce": 5.831989288330078, "genuineness": 3.9425034523010254, "identity": 0.08895353227853775, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/2743fd453df86b7548aae7410d092096595d8ffb249734467185863ad2984053.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "277a519d2beba158043b442e1db00bbe255eb11f049a4c66cbe6d1e55c714aa5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fb7f8856cf480e42962c8b61a3f1abfa19f3d5d4d5f19860cac069515faba5e0", "generation_seconds_batch": 20.4511669150088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0773757696151733, "target_z": 1.6484376012088948, "ce": 6.181467056274414, "genuineness": 4.2374773025512695, "identity": 0.6053124666213989, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/277a519d2beba158043b442e1db00bbe255eb11f049a4c66cbe6d1e55c714aa5.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "277ad175793ca3b62179f385bdb2c6bed3e6c62e022e5ccb71ecdf6755f76e30", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b93f0007073b2f886343ec6385bf5373d7da3c64013c3a1be1cec7137c4d130", "generation_seconds_batch": 19.437839750084095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.585896372795105, "target_z": 0.7031250555305442, "ce": 6.141753673553467, "genuineness": 4.080576419830322, "identity": 0.5826337337493896, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/277ad175793ca3b62179f385bdb2c6bed3e6c62e022e5ccb71ecdf6755f76e30.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": "27f1cc558c863a14676845ef405eeee0b64bf73ed386cf6a6b4e96aea40f2612", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Escribí el número en el sobre.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da4c963bc5ca7334bff8480476977e11d6f3dbb14706939213239844c0994196", "generation_seconds_batch": 17.492623485974036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3162286281585693, "target_z": 4.031249896104144, "ce": 6.23706579208374, "genuineness": 4.20609712600708, "identity": 0.6974565386772156, "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_Pride/27f1cc558c863a14676845ef405eeee0b64bf73ed386cf6a6b4e96aea40f2612.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "285f3f0a4e4ea58359dee4e4a48c677d6f93fd8e1d23c846e2f39c80a5f44afc", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 130, "seconds_generated": 10.4, "mp3_sha256": "72e58fbe7f4bfcb8847f235d5efcdb369f0d13a8fda7c8c95c2e144a6356259b", "generation_seconds_batch": 16.563829676015303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.45353627204895, "target_z": 6.218749903269375, "ce": 5.903473377227783, "genuineness": 3.936227321624756, "identity": 0.5984823107719421, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo está.", "wer": 0.13333333333333333, "duration_error_s": 0.20000000000000107, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/285f3f0a4e4ea58359dee4e4a48c677d6f93fd8e1d23c846e2f39c80a5f44afc.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": "28ad2e3bee5c959abfd0063283ad0a18d62ae240219070b338a8a6d2a1ed9e96", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "58e5c908fc348d96872198960aaf2d2382784c1089907984fbebf456c5ad8717", "generation_seconds_batch": 20.252952118986286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5229382514953613, "target_z": 0.5820312674652518, "ce": 6.268836498260498, "genuineness": 3.986435890197754, "identity": 0.6332581043243408, "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_Pride/28ad2e3bee5c959abfd0063283ad0a18d62ae240219070b338a8a6d2a1ed9e96.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": "28c7a9edc46532e389343250b108b3918995686e2f289ea7fb899c6ebd929e7c", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f72d56d33c5c6b46307f0a7b78a01703aae415ccd9874f5d755368439060cda3", "generation_seconds_batch": 19.12821916898247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4802892208099365, "target_z": 0.500000028660926, "ce": 6.141753673553467, "genuineness": 3.873466968536377, "identity": 0.6799448728561401, "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_Pride/28c7a9edc46532e389343250b108b3918995686e2f289ea7fb899c6ebd929e7c.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "297f879a05237b775645a670986b84f144232d82ca559e16f83b038f7e0c3d82", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e80f297cac770d0bdefcea37c7e07f531fab868fa35d2fc8789d36181a3d2c22", "generation_seconds_batch": 18.56346158706583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.992077648639679, "target_z": 1.4843750089565393, "ce": 6.038498878479004, "genuineness": 3.898571252822876, "identity": 0.6168733239173889, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/297f879a05237b775645a670986b84f144232d82ca559e16f83b038f7e0c3d82.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "2a6799164470eadfd70844d29b241b60b849833b3d6bb31109e0e1780d6f3a07", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "efdbe58afcff13dcd931f9eaa24d6f5be1c031ddd400b8a890a91f51ad923756", "generation_seconds_batch": 14.160279094008729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7638221979141235, "target_z": 2.9687501612177085, "ce": 6.0146708488464355, "genuineness": 4.268857479095459, "identity": 0.5226403474807739, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle connaît.", "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_Pride/2a6799164470eadfd70844d29b241b60b849833b3d6bb31109e0e1780d6f3a07.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": "2ae7005947ff0ab39fa5e2e907b6db215d15ad0e5dfded1fbe1ef32402930be8", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "17137173d003f05fbdf4fbe535fdab227e3f6e3e64ac726fd53e84fbe52a2657", "generation_seconds_batch": 22.57565895805601, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47419649362564087, "target_z": 0.48828126388263604, "ce": 6.054384231567383, "genuineness": 4.306513786315918, "identity": 0.577928900718689, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/2ae7005947ff0ab39fa5e2e907b6db215d15ad0e5dfded1fbe1ef32402930be8.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "2af132ef1a690517768ea494eaeab2520282d287a289dff8a6a127e1842e9e43", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3fcf28ba947c7ff905945851a5151b71b0bce7413cb5f701806ae3e6d91207ec", "generation_seconds_batch": 22.765271257958375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5919890403747559, "target_z": 0.7148437056651301, "ce": 6.38003396987915, "genuineness": 4.369274139404297, "identity": 0.5837920308113098, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/2af132ef1a690517768ea494eaeab2520282d287a289dff8a6a127e1842e9e43.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "2bbe812afdd3f1abad463342ead4c471efde35a6f6cdf08420ca33c0aa0c538a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "36a2961558335349ca35baa74751d17df81fb8ff95ec0df8d0c79126e0871fff", "generation_seconds_batch": 18.6241760289995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9100474119186401, "target_z": 3.250000057321852, "ce": 6.372091293334961, "genuineness": 3.9801597595214844, "identity": 0.5135601758956909, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/2bbe812afdd3f1abad463342ead4c471efde35a6f6cdf08420ca33c0aa0c538a.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "2c06996933b7991d716ac3cce786c2dac2ed6a5b796fa5fedccdabcf25e255b8", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "002160a0c7fa8940cacb56d90f059ddd0f4fbf667a432b32dee0c18cbffcd7f3", "generation_seconds_batch": 14.22510407899972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4957425594329834, "target_z": 2.453125198835174, "ce": 6.181467056274414, "genuineness": 3.9425034523010254, "identity": 0.1728871911764145, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/2c06996933b7991d716ac3cce786c2dac2ed6a5b796fa5fedccdabcf25e255b8.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "2c0a99236c03377502041e63f41f5e80da35a0778dd95acf9a440032bbed7258", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e559b3e3c14cfa5d8776679207969a45b0dd5339f344bb0e6fa5dc13eb1b57b8", "generation_seconds_batch": 15.714072462986223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1375088691711426, "target_z": 3.6874999211824533, "ce": 6.443574905395508, "genuineness": 3.7291181087493896, "identity": 0.4819640815258026, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/2c0a99236c03377502041e63f41f5e80da35a0778dd95acf9a440032bbed7258.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "2c0eba803cfd4b6c241b66f07bdc08829da91a432748a3c6284f7e5e793f4589", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c711bafc273a335c842e3473a1b3c8b54af43558e4a93420b861ecdd68871cd", "generation_seconds_batch": 13.768702864996158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6427617073059082, "target_z": 0.8124999641738425, "ce": 6.205295085906982, "genuineness": 4.193545341491699, "identity": 0.48169898986816406, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "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_Pride/2c0eba803cfd4b6c241b66f07bdc08829da91a432748a3c6284f7e5e793f4589.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "2c8a968bbbc98003126948ac5d3374ef2080b71ab26d23c80e9444a6f4de82c5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "514109fecdf32ec1899563bd84ed9aa914602375805b6117255e7f8211ecba72", "generation_seconds_batch": 19.080924805020913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9433358907699585, "target_z": 1.3906250053739235, "ce": 6.324435234069824, "genuineness": 4.268857479095459, "identity": 0.6610963344573975, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/2c8a968bbbc98003126948ac5d3374ef2080b71ab26d23c80e9444a6f4de82c5.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "2cc2ca53c00837c9c25dd1eac6294f14f6528186e365c50c6d2878253f42d607", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "08c6273509e5ac383025ab1f613fd5cf12f3d55f2603f88de8340bf9ac152682", "generation_seconds_batch": 13.861822366947308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2276628017425537, "target_z": 1.9375000071652315, "ce": 5.863759994506836, "genuineness": 4.011539936065674, "identity": 0.6827090978622437, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/2cc2ca53c00837c9c25dd1eac6294f14f6528186e365c50c6d2878253f42d607.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "2cc5f80c06a17aa2e70b15a336a0594902851ecefa65be2dccdfe923cef468ee", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c61fa688d8eeb03d2ec2f0b6b6ed9e6e6baa52e271654bc8dba96b4251cea135", "generation_seconds_batch": 18.52793327101972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8824086785316467, "target_z": 1.273437472234728, "ce": 6.173524379730225, "genuineness": 4.030367851257324, "identity": 0.39882540702819824, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/2cc5f80c06a17aa2e70b15a336a0594902851ecefa65be2dccdfe923cef468ee.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "2d2d08f617f4f4bf3749b4def004ef0aa1b8276cee2e81f576c4c41a1717d43d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a1100c3f781c9fa7695025e90b0edf85d32256fa5bb5fc4be75a3c13a5665ef1", "generation_seconds_batch": 22.105004520970397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7849251627922058, "target_z": 1.0859374650694964, "ce": 6.300607204437256, "genuineness": 4.375550270080566, "identity": 0.8122637271881104, "hypothesis": "J'ai trouvé la 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_Pride/2d2d08f617f4f4bf3749b4def004ef0aa1b8276cee2e81f576c4c41a1717d43d.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": "2d5ccac3f4d88c4c4bd260363db1aab14db7b085f4e0fcaa15898edc8a76bc89", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b1179fd8b7b6210b7cfc0ef08888a82ada4ea3546d414683b523eb71496afef", "generation_seconds_batch": 13.796595033025369, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3487231731414795, "target_z": 4.09374997492169, "ce": 6.284721851348877, "genuineness": 4.419482707977295, "identity": 0.7786660194396973, "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_Pride/2d5ccac3f4d88c4c4bd260363db1aab14db7b085f4e0fcaa15898edc8a76bc89.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": "2d9a61470d03318661c0688450f00993483787436b89e5781b857caa867f2841", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "194788f9630b327612c7c6111f3f88cd3dea71eb3b5d31bbbba478f5ae1ab0fd", "generation_seconds_batch": 20.252952118986286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6021435856819153, "target_z": 0.7343749802956133, "ce": 6.324435234069824, "genuineness": 3.9299514293670654, "identity": 0.5315598845481873, "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_Pride/2d9a61470d03318661c0688450f00993483787436b89e5781b857caa867f2841.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "2db6e180af802a32964761cb0f44c53288e7db6b639d5baad81afd89d8c49a66", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1f0d249c89b2cdefbe47afd70a658b6edc8bf9354eeb7097b5d8da155a1db96a", "generation_seconds_batch": 21.80047111492604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.723997950553894, "target_z": 0.9687499319303008, "ce": 6.086154937744141, "genuineness": 3.848362922668457, "identity": 0.7343467473983765, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/2db6e180af802a32964761cb0f44c53288e7db6b639d5baad81afd89d8c49a66.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": "2e843457cb007a9acbc766da2d7f99e50a4bc430025e1243d9461d7007bbce53", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I wrote the number on the envelope.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "01b49f6460d1230de2a4d51a4cd20f5b98e2c6292b5ee3b283af2ce82c33d65b", "generation_seconds_batch": 14.44282476499211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.869429349899292, "target_z": 3.171875188087327, "ce": 6.3641486167907715, "genuineness": 3.625563621520996, "identity": 0.34614014625549316, "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_Pride/2e843457cb007a9acbc766da2d7f99e50a4bc430025e1243d9461d7007bbce53.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "2ea4ede599c83e8f2e21ef78e5c517269201e555057bfaf4140f24ee46911e27", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d29af4444a70a3c222ddabac763d604c9b4b14c647273867082de25f6349b162", "generation_seconds_batch": 19.50503546500113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3820117712020874, "target_z": 2.2343751522611695, "ce": 6.268836498260498, "genuineness": 4.149612903594971, "identity": 0.4246746301651001, "hypothesis": "J'ai trouvé la 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_Pride/2ea4ede599c83e8f2e21ef78e5c517269201e555057bfaf4140f24ee46911e27.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "2fece01c651523c43d8abdc9c80d61cdc953765ebd291195d5f7a81bd72477e9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fbc567d83af47d43e33cb473881ef7ec6c95cb05fffa497d348b62557ef74203", "generation_seconds_batch": 13.737886777962558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0936230421066284, "target_z": 1.6796876406176682, "ce": 6.078212261199951, "genuineness": 4.15588903427124, "identity": 0.5766689777374268, "hypothesis": "J'ai trouvé la 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_Pride/2fece01c651523c43d8abdc9c80d61cdc953765ebd291195d5f7a81bd72477e9.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "301bec96109c74f8c7a42be96617df1f7f3dbcfc1d5b9f8c88fca2ab05262f22", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "543bc44ed5fb8abf90c9a94d883e48bf294982d1e50d28e1df386b09df247b48", "generation_seconds_batch": 20.14193001005333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5201133489608765, "target_z": 2.500000028660926, "ce": 5.895530700683594, "genuineness": 3.9173994064331055, "identity": 0.3574885129928589, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/301bec96109c74f8c7a42be96617df1f7f3dbcfc1d5b9f8c88fca2ab05262f22.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "302bfcdb7f83fb82938fdea6af2cf2aec6e6c571e82a0999be8b8f49c065d53e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "6d557cf9fb47242e6087c556d0edcb35e81ef96f4d239ed28533c52dc7a7ce92", "generation_seconds_batch": 21.478428832022473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2439100742340088, "target_z": 1.9687500465740047, "ce": 5.808161735534668, "genuineness": 3.9048471450805664, "identity": 0.6216423511505127, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/302bfcdb7f83fb82938fdea6af2cf2aec6e6c571e82a0999be8b8f49c065d53e.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "30dedb2da41c1cb7e7fa31b4eacf241f1a619b0474debc52ecd4ef7579a7af06", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "81e5f0a34e9f25ddde3d8d59fa138c7b6b1b6506e0ed27a396ddf2d127e308eb", "generation_seconds_batch": 18.61781287100166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9595831036567688, "target_z": 1.4218749301389928, "ce": 6.252951145172119, "genuineness": 3.9801597595214844, "identity": 0.69051194190979, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/30dedb2da41c1cb7e7fa31b4eacf241f1a619b0474debc52ecd4ef7579a7af06.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "30fe17882c621970e1aca3cc4c8dba64bc5ec08e35ea6552fe402c925f5e45c0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 130, "seconds_generated": 10.4, "mp3_sha256": "48f36843601c4a54cebc1111b353d250a9f0a274d61873afca0430a7995b2d7d", "generation_seconds_batch": 18.997785553103313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7638221979141235, "target_z": 2.9687501612177085, "ce": 5.816103935241699, "genuineness": 3.9048471450805664, "identity": 0.5164079070091248, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "wer": 0.06666666666666667, "duration_error_s": 0.20000000000000107, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/30fe17882c621970e1aca3cc4c8dba64bc5ec08e35ea6552fe402c925f5e45c0.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "31172d8dbb78849585052c43e9d134e916fbc21c395c03dba9458624992e85ae", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "77f8a91df139f391dbd188151868e7b825957bdbfd580855cab8fa3f0089f4ac", "generation_seconds_batch": 22.624385284027085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1301792860031128, "target_z": 1.75, "ce": 5.967014789581299, "genuineness": 3.8546390533447266, "identity": 0.6825469732284546, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/31172d8dbb78849585052c43e9d134e916fbc21c395c03dba9458624992e85ae.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "315aafbc1c6d4a8040a514ede3fdc13d4572ce59e2fb4bb39a0c58bda304930b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1ffb439b68edc30c7bada2c190745b18c3b7e8cda202eac40be3f82e04422b24", "generation_seconds_batch": 20.672739790054038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42443928122520447, "target_z": 0.39257813283697196, "ce": 6.054384231567383, "genuineness": 4.149612903594971, "identity": 0.6975038647651672, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/315aafbc1c6d4a8040a514ede3fdc13d4572ce59e2fb4bb39a0c58bda304930b.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "3194da9918cf3c4a74aa699274b0339b47c9e62734b255cbccf476cbe4769984", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2218f0f9c96b08aae068c18d93eae4dcb70f3ba5ca4027a46f5fecb62a2a3411", "generation_seconds_batch": 20.772530908929184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9717685580253601, "target_z": 1.4453124596955729, "ce": 6.23706579208374, "genuineness": 4.250029563903809, "identity": 0.6868537068367004, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3194da9918cf3c4a74aa699274b0339b47c9e62734b255cbccf476cbe4769984.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "329e54be3b68e73978e98eb9a5bec7a18ae465804aecf34466db381025603f40", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "45824fcf4fe7b7b5dcc7cd787fb431855f46c83412638854c344582a896e7364", "generation_seconds_batch": 18.629002745030448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.951459527015686, "target_z": 1.4062500250783103, "ce": 5.772419452667236, "genuineness": 3.8546390533447266, "identity": 0.5698797702789307, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/329e54be3b68e73978e98eb9a5bec7a18ae465804aecf34466db381025603f40.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "32c2dde626d52f4903f169a013a88b0071858508f612fad918498d7cbbe44838", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4f427e1306a11ed7b8d1f50b1e08142b3147aef6855ffc88312d32c77ddbbd57", "generation_seconds_batch": 19.118080600979738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5452781915664673, "target_z": 0.624999957008611, "ce": 6.157639026641846, "genuineness": 4.356721878051758, "identity": 0.5942593812942505, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/32c2dde626d52f4903f169a013a88b0071858508f612fad918498d7cbbe44838.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "32dff5c4a0bf7228a59af042d4519cfb9ca64824a2d48309b50ab3f808edef67", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2277a65979c1ce42471eb5c8d3fb416d86bffc4f9aa64a63f6d9f8e4a73057c0", "generation_seconds_batch": 21.147971534985118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5363606214523315, "target_z": 2.531250068069699, "ce": 6.109982967376709, "genuineness": 4.030367851257324, "identity": 0.3503642678260803, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/32dff5c4a0bf7228a59af042d4519cfb9ca64824a2d48309b50ab3f808edef67.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "32f809879c9b39ac829bd9d0ae6e9347b0fbbe43d852eb23687a1ab4e7ca5f27", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6c867728f0edc67ee67239b9b11212048aa880639f020108865c6e62131ad77f", "generation_seconds_batch": 21.142344138002954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.126117467880249, "target_z": 1.7421874901478067, "ce": 6.427689552307129, "genuineness": 4.406930446624756, "identity": 0.6109932661056519, "hypothesis": "J'ai trouvé la 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_Pride/32f809879c9b39ac829bd9d0ae6e9347b0fbbe43d852eb23687a1ab4e7ca5f27.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "332db9082cbeec3fd22b12098db81584704c60d35d87ff351035a4e398113edb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "89a09d77e0034171a3ae77361403c4600e80a3d2a8e53fad47fade08a52afc95", "generation_seconds_batch": 15.523317924933508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9027177691459656, "target_z": 1.3125000214956946, "ce": 6.308549880981445, "genuineness": 4.168440818786621, "identity": 0.20723067224025726, "hypothesis": "I fOND 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_Pride/332db9082cbeec3fd22b12098db81584704c60d35d87ff351035a4e398113edb.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "3379d60793e9d3f7af02e60c9f9c88459900c6f642cdf6729eb6933db917d316", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dfe0098e1d7cfc863474f6654794b0d4a1236891c096732f5f6b719762f579b5", "generation_seconds_batch": 20.91935714299325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5940199494361877, "target_z": 0.7187499605912268, "ce": 6.165581703186035, "genuineness": 4.457139015197754, "identity": 0.7143377065658569, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3379d60793e9d3f7af02e60c9f9c88459900c6f642cdf6729eb6933db917d316.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": "33d2b23ee86ba893a4e769a7f334319a00132cad44cba181049d8c213607d7a6", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9bc53e86d5de79874c13410e3845c002ac95cf23965419ca306e4c7029b8f191", "generation_seconds_batch": 21.031190215959214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0530048608779907, "target_z": 1.6015625420957351, "ce": 6.300607204437256, "genuineness": 4.243753433227539, "identity": 0.4577087163925171, "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_Pride/33d2b23ee86ba893a4e769a7f334319a00132cad44cba181049d8c213607d7a6.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "5e5b6816f8e17d04bae1747e09a7975263270d3b096d97e90c65ab2a3cbb3d8c", "generation_seconds_batch": 17.498938789009117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3066467046737671, "target_z": 0.1660156337326259, "ce": 6.125868320465088, "genuineness": 4.344170093536377, "identity": 0.8070608973503113, "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_Pride/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.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": "34774b873ffc8a8c9083afb50a3cf9921e1e0951ea23338262351cf21e80d64d", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9019e4808e25a0935320a0ffae89b08017ab46cee51ad7bf5ac39741fa9bccce", "generation_seconds_batch": 13.796595033025369, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.462453842163086, "target_z": 4.312499792208286, "ce": 6.229123115539551, "genuineness": 4.262581825256348, "identity": 0.6884790658950806, "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_Pride/34774b873ffc8a8c9083afb50a3cf9921e1e0951ea23338262351cf21e80d64d.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "02d33c9bb9f08beb84fc5b20ab6a0d07b3d42b4fb9a714bc858ef5720b46bcc1", "generation_seconds_batch": 14.143004130921327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4701346755027771, "target_z": 0.4804687540304427, "ce": 6.459460258483887, "genuineness": 4.15588903427124, "identity": 0.2161540985107422, "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_Pride/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "34e09572e8e0eeb418f395f2e0275bb07f7c1553394d183ec26e912552d00263", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "a953333cc915f7d870ab14888a3fda2145de6ed6095afe567c32d73eedd7fdcc", "generation_seconds_batch": 14.261693430016749, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.511989712715149, "target_z": 2.4843750089565395, "ce": 5.847874641418457, "genuineness": 3.8044304847717285, "identity": 0.6114514470100403, "hypothesis": "De deur 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_Pride/34e09572e8e0eeb418f395f2e0275bb07f7c1553394d183ec26e912552d00263.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "34e12cfbb38344ebc74a83d11b4ee5d5744ac81245173a0d2fe89e7881865c5d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c9f22e946445966f392d32cc6407da7d76e9c51fddd94ac13a2373293df729d1", "generation_seconds_batch": 21.404209358035587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49247461557388306, "target_z": 0.523437443573802, "ce": 6.133810997009277, "genuineness": 4.149612903594971, "identity": 0.6911029815673828, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/34e12cfbb38344ebc74a83d11b4ee5d5744ac81245173a0d2fe89e7881865c5d.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "353096f9f2aec65b45fa468b5c35ed47d47833daded024bfc3d0b8f0a23bf1fb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e931f1fb8fbe9eb0193c81f64464b8e5f767581e5192b9042f7bb9eac49d63ad", "generation_seconds_batch": 18.441480853012763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6082363128662109, "target_z": 0.7460937450739034, "ce": 6.173524379730225, "genuineness": 4.193545341491699, "identity": 0.5921154022216797, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que ha hecho.", "wer": 0.11764705882352941, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/353096f9f2aec65b45fa468b5c35ed47d47833daded024bfc3d0b8f0a23bf1fb.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "353e6e105c314ab2a8e222c94f8d9475874691f73b9e43775d485cfa590755e7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "87d6a08506c6339ced762f72cd0e44e05df69e7c4198058ffd9d61daa412aa8b", "generation_seconds_batch": 20.840067739016376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6915034651756287, "target_z": 0.9062499677564583, "ce": 6.260893821716309, "genuineness": 4.030367851257324, "identity": 0.32734358310699463, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/353e6e105c314ab2a8e222c94f8d9475874691f73b9e43775d485cfa590755e7.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": "360cae85286d4a1f8c4777ecce282dfc3d44860d0e35edd3f81a6aebb1b99cf4", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Your message arrived after I had left.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f5c0ba6811aa409836f157efcae7953274b6d89ecb71a46e6274c02162309c8f", "generation_seconds_batch": 15.670576137956232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.585896372795105, "target_z": 0.7031250555305442, "ce": 6.4515180587768555, "genuineness": 4.118232727050781, "identity": 0.31174299120903015, "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_Pride/360cae85286d4a1f8c4777ecce282dfc3d44860d0e35edd3f81a6aebb1b99cf4.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "36e403533310425aa588cf9acfcf10df1f2a772c4e113aedf0a8b9c4a31f08b3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "de1c3007c8d0c7f759bfc3b08046288505aec1688b713475fd70d9e38f55f13d", "generation_seconds_batch": 20.587215051054955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1383029222488403, "target_z": 1.7656250197043866, "ce": 6.252951145172119, "genuineness": 4.457139015197754, "identity": 0.707574188709259, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/36e403533310425aa588cf9acfcf10df1f2a772c4e113aedf0a8b9c4a31f08b3.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "3788756d8007f78739246b13242138869fbf479a9316b7a8df2c407410b5bf43", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "65b2146f340e5f708f500aa6759eaa3e11c8deff35ca6f6060efdf2c49e4c407", "generation_seconds_batch": 15.173866345081478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1058083772659302, "target_z": 1.70312494088684, "ce": 6.173524379730225, "genuineness": 3.810706615447998, "identity": 0.3132161498069763, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3788756d8007f78739246b13242138869fbf479a9316b7a8df2c407410b5bf43.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "37b13ff85aa5eb2ca6a7d3bf6f519afe02718e46e409dab7985a7eabd0fa66ce", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ec2822046a23f1e9ed1d32650e6339826cd7dbc068234f23f71dca866ac9d0f6", "generation_seconds_batch": 18.827744669979438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9506655931472778, "target_z": 3.328125155843785, "ce": 5.911416053771973, "genuineness": 4.13078498840332, "identity": 0.18957222998142242, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereitst.", "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_Pride/37b13ff85aa5eb2ca6a7d3bf6f519afe02718e46e409dab7985a7eabd0fa66ce.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": "37b7579f3df5e105dad7a9036fd4dd5ca03700d63daf466ad15706ea44cd8b56", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The road turns left behind the bridge.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "461aa3e68454dcd10c66fa3cf08aad075a4051b9e07bccf5184f99acddcc74a7", "generation_seconds_batch": 15.325923882075585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6711944341659546, "target_z": 0.8671875331391957, "ce": 6.3641486167907715, "genuineness": 4.024092197418213, "identity": 0.3688786029815674, "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_Pride/37b7579f3df5e105dad7a9036fd4dd5ca03700d63daf466ad15706ea44cd8b56.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "37fd5bcd96fb3ed1e82d77414bbb0ce19ba7ab291a958054350c453a56758dd6", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "18f5bc41fbe77d3bf1c4f494f0d3df22d97d0cc6e44edc757e0b4f15dd5eba24", "generation_seconds_batch": 22.765271257958375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6996271014213562, "target_z": 0.9218749874608448, "ce": 6.348263263702393, "genuineness": 4.20609712600708, "identity": 0.4677082896232605, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/37fd5bcd96fb3ed1e82d77414bbb0ce19ba7ab291a958054350c453a56758dd6.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "38e4f7ddf57a88b8c2d2c8100c211e356918e24130f4f222565b85ff43467523", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "39a66a80c3e4f5ac92bd1335a86831115b9e2228fb8e8f43c295491e688cec0e", "generation_seconds_batch": 22.80045954999514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9108413457870483, "target_z": 1.328124926556377, "ce": 5.796247482299805, "genuineness": 4.193545341491699, "identity": 0.5240511894226074, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/38e4f7ddf57a88b8c2d2c8100c211e356918e24130f4f222565b85ff43467523.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "393747fc9fa5a788fcdcfd3bba8d8dc64b4a358f6a22c44517ddae501552c3ba", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "26d87b8cc4e1b08c00ba5ea370bb80c9f7b0c71619245a4ba66148934fb3d5fa", "generation_seconds_batch": 21.84047155699227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2154773473739624, "target_z": 1.9140624776086517, "ce": 6.157639026641846, "genuineness": 4.093128204345703, "identity": 0.4086970090866089, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "wer": 0.058823529411764705, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/393747fc9fa5a788fcdcfd3bba8d8dc64b4a358f6a22c44517ddae501552c3ba.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "393df257c0c661552c2eb77314287ee3810187d3ac278311d5e901d02d45831c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3cd2f8f5bbbe35c7ba826f43c7ba4c7b0df1a3fe0fd8f607a01d57e2b75d767e", "generation_seconds_batch": 20.672739790054038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5737109184265137, "target_z": 0.6796875259739642, "ce": 6.109982967376709, "genuineness": 4.18099308013916, "identity": 0.6554473638534546, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/393df257c0c661552c2eb77314287ee3810187d3ac278311d5e901d02d45831c.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "3958243df67dbc673b55a613da55781bb440537ddd44943fce597d2c32633516", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b9f011941fdb5fea7270941c264237c1b375b1b38876f33e0da8b0b02ddda79d", "generation_seconds_batch": 22.359814755036496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8417905569076538, "target_z": 1.1953124883564987, "ce": 6.149696350097656, "genuineness": 4.21237325668335, "identity": 0.4688413739204407, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3958243df67dbc673b55a613da55781bb440537ddd44943fce597d2c32633516.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "39991133688a919749620aa7f5f96e1652f34f1962610cd8e4db6b253be9d6b2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d8ca70944065ebafe1f48240ace753b1cbfc6dbaaf310afa3240c544af9cd764", "generation_seconds_batch": 15.241453648079187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8686351776123047, "target_z": 5.093749860277986, "ce": 6.403861999511719, "genuineness": 4.13078498840332, "identity": 0.5792237520217896, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/39991133688a919749620aa7f5f96e1652f34f1962610cd8e4db6b253be9d6b2.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "39ec2f51973387d0341be1e999af8e77f1a195a967c117fbed449a7e36e8cc22", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5f0ec87142260d95042eee903fde33fb9cfdfb233834da3d32cb47ea32b7e7bb", "generation_seconds_batch": 20.293878283002414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9839540123939514, "target_z": 1.4687499892521527, "ce": 6.022613525390625, "genuineness": 4.061748504638672, "identity": 0.5331762433052063, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/39ec2f51973387d0341be1e999af8e77f1a195a967c117fbed449a7e36e8cc22.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": "3ab9254a8b3e35f9ff38ceb3e557ad8c993a07812e7dd75c39ed23dac2b7012d", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "72719b467fe28ab5e61b2842ec0c251558c8c0cfc36bdc77f70248462d25afc6", "generation_seconds_batch": 22.60464243509341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1342411041259766, "target_z": 1.7578125098521933, "ce": 6.2767791748046875, "genuineness": 4.030367851257324, "identity": 0.6339777708053589, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grand bibliothèque. Nous la remettrons afin 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_Pride/3ab9254a8b3e35f9ff38ceb3e557ad8c993a07812e7dd75c39ed23dac2b7012d.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "3b95b499320f1ba7dffd5b9d4c6b4810f4d0eb3e943737bec8e238fcb14608b2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "40c828e3beac5ba8b262b7cce9a89ba8b38ad335169865997b96c229eb2c496e", "generation_seconds_batch": 20.66052721592132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1375088691711426, "target_z": 3.6874999211824533, "ce": 6.324435234069824, "genuineness": 3.773050308227539, "identity": 0.320296049118042, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3b95b499320f1ba7dffd5b9d4c6b4810f4d0eb3e943737bec8e238fcb14608b2.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "3be5165206d6a1fa9569e7b9e1f1e25c57f78c04dddc8165e2a47526a0e6c79a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cfe50d15ee97acfab4dec0d2d6814e33a16c2ebb21dbc72301320db74aed2072", "generation_seconds_batch": 13.729134320979938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3332699537277222, "target_z": 2.1406250340348496, "ce": 6.2767791748046875, "genuineness": 4.18726921081543, "identity": 0.507685661315918, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3be5165206d6a1fa9569e7b9e1f1e25c57f78c04dddc8165e2a47526a0e6c79a.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": "3c44d0dafe4d26ffc76e323bdc807e3bd738f12034c9520625ca03f7b6faa8ea", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The road turns left behind the bridge.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9cf645c75c553f4aa1b7b6d554ca611386f02e1abf91d0c75b213796ef30812f", "generation_seconds_batch": 15.325923882075585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5777727365493774, "target_z": 0.6875000358261575, "ce": 6.403861999511719, "genuineness": 3.961331605911255, "identity": 0.40314269065856934, "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_Pride/3c44d0dafe4d26ffc76e323bdc807e3bd738f12034c9520625ca03f7b6faa8ea.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "3c4d2f8643ecd83477a9eca0f7fb28de06f2237bebffbe8d06ebf45625aef695", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dc184b764f74a333b11d4a9f4435b5d4ab0345ccdff08ac7ac6da0c2fcb030dd", "generation_seconds_batch": 21.81381840899121, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.390135407447815, "target_z": 2.250000171965556, "ce": 5.998785495758057, "genuineness": 4.231201171875, "identity": 0.46173226833343506, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We 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_Pride/3c4d2f8643ecd83477a9eca0f7fb28de06f2237bebffbe8d06ebf45625aef695.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "baf90d41eb223ce4e3e22cb792b14e53c29e31f00f7a2412fffd56f52850ea0b", "generation_seconds_batch": 16.57901625998784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4701346755027771, "target_z": 0.4804687540304427, "ce": 6.308549880981445, "genuineness": 4.256305694580078, "identity": 0.5595155954360962, "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_Pride/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.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": "3ce9378192ec47aa929c49d8423bd8d9fb5d1734f687ac9079cc47092b2a9850", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I wrote the number on the envelope.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a5a33c93b4aa62fdc0690bd093ac76be727ae731bc1cc87b56131bd0ee646f4", "generation_seconds_batch": 14.44282476499211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8044402599334717, "target_z": 3.046875030452234, "ce": 6.340320587158203, "genuineness": 3.7040140628814697, "identity": 0.27804189920425415, "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_Pride/3ce9378192ec47aa929c49d8423bd8d9fb5d1734f687ac9079cc47092b2a9850.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": "3cee0b6ad81df2a18f335f52a54fe93509976862af2bba138fac2bb163df1232", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Someone moved the little blue chair.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97a1f1290fc122456b12a9de8a769670819c3cf510c560e757bef969bc3baf75", "generation_seconds_batch": 14.889388252981007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3594502806663513, "target_z": 0.26757814716743494, "ce": 6.41180419921875, "genuineness": 4.118232727050781, "identity": 0.14607730507850647, "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_Pride/3cee0b6ad81df2a18f335f52a54fe93509976862af2bba138fac2bb163df1232.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "3cf64e69105568a76467ba3680df6d57736bd4e4d444439cc8d3698d83e4a3c8", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4bd674da4a14dc366a45a26389c2d8a75c3c8a9ef861066b33da6ad0280f20d5", "generation_seconds_batch": 22.84072462504264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8288111686706543, "target_z": 3.0937500895653938, "ce": 6.300607204437256, "genuineness": 4.055472373962402, "identity": 0.04175567626953125, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3cf64e69105568a76467ba3680df6d57736bd4e4d444439cc8d3698d83e4a3c8.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "3d26abcb18b9039fe6d4c56f488bd8249f08700a7002c36cad193c7ea09b298c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "561d5be0fce2e18b132f971888a1528ad0ae25729c34eddec92bf3bcab2efee1", "generation_seconds_batch": 22.666839297977276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6813489198684692, "target_z": 0.886718693125975, "ce": 6.062326908111572, "genuineness": 3.8671910762786865, "identity": 0.7321778535842896, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3d26abcb18b9039fe6d4c56f488bd8249f08700a7002c36cad193c7ea09b298c.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "3da682f5bcbb25db9cee59fb6a2234724dc5b924b13f6cf27c8f02cf8326ace5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "987ed63c8a57b8aaadffb53f562f7764cdbf188217e84d72e2cd79f9fdf1b68a", "generation_seconds_batch": 21.294776351074688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9636449217796326, "target_z": 1.429687439991186, "ce": 5.927301406860352, "genuineness": 3.7416701316833496, "identity": 0.47457534074783325, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3da682f5bcbb25db9cee59fb6a2234724dc5b924b13f6cf27c8f02cf8326ace5.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "3dde709a039f192b3739faaaece5f58d2b9b5c99309b1e45098e721f8e019b56", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "02dcf1cb543d7bcba396527bb9f24153671678a748c052b15f699c69494da634", "generation_seconds_batch": 20.587215051054955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1058083772659302, "target_z": 1.70312494088684, "ce": 6.260893821716309, "genuineness": 4.356721878051758, "identity": 0.5759832859039307, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3dde709a039f192b3739faaaece5f58d2b9b5c99309b1e45098e721f8e019b56.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": "3dfc4ff049757b7312cd368789fcd5a03a8895bf8cb43358e734ab94bb2e8020", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "626f008de9c0fe68e1ee10b6dbf73bb0836d3d098548d953e32445d16de4bbc7", "generation_seconds_batch": 22.252622817992233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6183908581733704, "target_z": 0.7656250197043867, "ce": 6.340320587158203, "genuineness": 4.055472373962402, "identity": 0.6318378448486328, "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_Pride/3dfc4ff049757b7312cd368789fcd5a03a8895bf8cb43358e734ab94bb2e8020.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": "3e81b1f7aa58e76d31ebc6f83d58f5f021674ff86f316ebd27770cb4c98552c0", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "85dd08de41cf54126b4e89368919ce2da22b69bf1c845ac6b92390fb717bd1e5", "generation_seconds_batch": 15.111752734985203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5534018278121948, "target_z": 0.6406249767129977, "ce": 6.221180438995361, "genuineness": 4.20609712600708, "identity": 0.4468998908996582, "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_Pride/3e81b1f7aa58e76d31ebc6f83d58f5f021674ff86f316ebd27770cb4c98552c0.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "3ebd4881c9a152da1808375ea31a8fda2e20a8e0b9b73d64fecd35447776cf09", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "9bed4a57c844503e19dc63fb1095dcc46447b4d824418d00d9c1814c6afed13c", "generation_seconds_batch": 20.049703483004123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9027177691459656, "target_z": 1.3125000214956946, "ce": 5.824047088623047, "genuineness": 3.9801597595214844, "identity": 0.518280029296875, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "wer": 0.06666666666666667, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3ebd4881c9a152da1808375ea31a8fda2e20a8e0b9b73d64fecd35447776cf09.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "3edd8ca87bb05f92993e8ab11d4843fbb4e0d97278fd8f6a476157b53675eeae", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3c63ea1bff7b15c5c6e15ac6f5d3a3a12d18d8923431a5e1239d2529f02a0813", "generation_seconds_batch": 19.816462000948377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1545501947402954, "target_z": 1.79687505911316, "ce": 6.205295085906982, "genuineness": 4.055472373962402, "identity": 0.6243810057640076, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3edd8ca87bb05f92993e8ab11d4843fbb4e0d97278fd8f6a476157b53675eeae.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "3f00525a7a2780a7bf0384171a9692d579d76bbd65e1b058178ad340f3629c14", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "05cc6f2ad0093e77eb58249dfb94c9a97c63f486ebc7371aca878634f3e86d1b", "generation_seconds_batch": 21.478763755992986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.992077648639679, "target_z": 1.4843750089565393, "ce": 6.252951145172119, "genuineness": 4.193545341491699, "identity": 0.626173198223114, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3f00525a7a2780a7bf0384171a9692d579d76bbd65e1b058178ad340f3629c14.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "3f1b40ee98c7a4a1ae8d755cf12a4ff9ee6aa3144b1dea9583427464b1fd04fd", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "58add1ec8c3659e71117d2f007e656e9a2f4b33fe1aac0e017e001a5e850bc32", "generation_seconds_batch": 21.251813738956116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0002013444900513, "target_z": 1.50000014330463, "ce": 6.165581703186035, "genuineness": 4.011539936065674, "identity": 0.6018309593200684, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3f1b40ee98c7a4a1ae8d755cf12a4ff9ee6aa3144b1dea9583427464b1fd04fd.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": "3f208efea3e23e210894835682996ae81663d669230c78cbe13d3b3970337ee2", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d82fd52cc5531e86872841955101fefaf0e31933061a832231d0dac11ff53cfc", "generation_seconds_batch": 16.119979920913465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.178921103477478, "target_z": 1.8437501182263198, "ce": 6.3641486167907715, "genuineness": 4.243753433227539, "identity": 0.4685428738594055, "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_Pride/3f208efea3e23e210894835682996ae81663d669230c78cbe13d3b3970337ee2.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "3f326211d3b6dc16325162d64a24d3519ed892c0d6a9cb842a112e4c042097d9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fc9d7a77a24be2cbbc511c5f7c25fa1f314371703952fe2b11969c837502876e", "generation_seconds_batch": 18.621807985007763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9149031639099121, "target_z": 1.3359374364085705, "ce": 6.2767791748046875, "genuineness": 4.344170093536377, "identity": 0.6899637579917908, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3f326211d3b6dc16325162d64a24d3519ed892c0d6a9cb842a112e4c042097d9.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "3f70694a157b543c6ef0eab2061548854af5e8128c7a8338b457357f1bb711ed", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "84dfb0d3401b26a5043e065fe1751c1edf314683a616cea5cc233b428231047b", "generation_seconds_batch": 18.574098577955738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5412163734436035, "target_z": 0.6171874471564177, "ce": 6.268836498260498, "genuineness": 4.143336772918701, "identity": 0.278617799282074, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3f70694a157b543c6ef0eab2061548854af5e8128c7a8338b457357f1bb711ed.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "3f910642631386aae5db5bc34515c0957905b42e7a6a021322891c4cb8f714d3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ebd5c05306b6031ea3714b4dd380f556d99ddb86cfd716d63346f122ad1ddb3d", "generation_seconds_batch": 22.666839297977276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6691635251045227, "target_z": 0.8632812782130991, "ce": 6.1894097328186035, "genuineness": 3.986435890197754, "identity": 0.6771758794784546, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/3f910642631386aae5db5bc34515c0957905b42e7a6a021322891c4cb8f714d3.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "40adcba7c5c8835ea9ec42381dbcdc32cd2af705a98c8ed609a0758179afc8f5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "eedd0a73abda6cece7bc5225cd255570a6cc79b91f184a85e5f2c86d10393c36", "generation_seconds_batch": 13.958332704030909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7889869809150696, "target_z": 1.0937499749216897, "ce": 6.157639026641846, "genuineness": 4.344170093536377, "identity": 0.6587634086608887, "hypothesis": "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_Pride/40adcba7c5c8835ea9ec42381dbcdc32cd2af705a98c8ed609a0758179afc8f5.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "40be159d8cc9b512affe2b73376ed4e6699b9487e3919f8046f7c8681d57bbc2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b997f2b77503a6dbc022da688385af3d648bd8e94d49367f1c16da3702703f29", "generation_seconds_batch": 19.618525799014606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1545501947402954, "target_z": 1.79687505911316, "ce": 6.252951145172119, "genuineness": 4.394378662109375, "identity": 0.7330557107925415, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/40be159d8cc9b512affe2b73376ed4e6699b9487e3919f8046f7c8681d57bbc2.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "40d5b0c3cd7edb754f0bc0953c9bcebac81abf49366168681fc50a98b6e8a926", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "af11fa1586f45f780c85e637c1528b7e4d6cfefc40d0ded29da9f3bddf3f78a7", "generation_seconds_batch": 13.780542536987923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7097816467285156, "target_z": 0.9414062620913282, "ce": 6.23706579208374, "genuineness": 4.149612903594971, "identity": 0.6423410773277283, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/40d5b0c3cd7edb754f0bc0953c9bcebac81abf49366168681fc50a98b6e8a926.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "413b61d0166383e714b7e7a6c9a7b937bc53e2a38b2d386bb5f527ac94a37376", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "c5527bcea0911d0932294663fcd983d807802091ea6b0d0e998a531a5d3c0184", "generation_seconds_batch": 19.931992057012394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9392740726470947, "target_z": 1.3828124955217302, "ce": 5.903473377227783, "genuineness": 4.243753433227539, "identity": 0.5504975318908691, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que.", "wer": 0.11764705882352941, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/413b61d0166383e714b7e7a6c9a7b937bc53e2a38b2d386bb5f527ac94a37376.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "416347932e69ccd5ce32d32c2a1f5ea316c719bf59471be58a3d08c687a13a7d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3226ee72abfb4dca79c358b8a49b40a24d9096562fc6d8f4578be381d9f3e76d", "generation_seconds_batch": 19.053912485018373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7768015265464783, "target_z": 1.0703124453651098, "ce": 6.205295085906982, "genuineness": 4.413206577301025, "identity": 0.742843747138977, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/416347932e69ccd5ce32d32c2a1f5ea316c719bf59471be58a3d08c687a13a7d.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "416aeba34c8243cdc4f1cbe7733dfb33856edcb0b4a9ecc6052169f6d64ecbe3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "73c464c2db24fadc9cc65c63da24044e2640ccbd0a3af132332ac4f4e32a41ed", "generation_seconds_batch": 15.017204146948643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.203291893005371, "target_z": 1.8906249480520716, "ce": 6.1894097328186035, "genuineness": 4.300237655639648, "identity": 0.6420052647590637, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/416aeba34c8243cdc4f1cbe7733dfb33856edcb0b4a9ecc6052169f6d64ecbe3.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "41815af050f6f0c00f10c2a01f2db3397b9fb153fc6b3d8dbbb57f045fd0fcc4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8ef3f89b6de438bd3133128fa97735b31c2f6a0fe332deaa9a95d6ccff077ac6", "generation_seconds_batch": 19.809552451013587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.83772873878479, "target_z": 1.1874999785043054, "ce": 6.086154937744141, "genuineness": 4.331617832183838, "identity": 0.5326313972473145, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/41815af050f6f0c00f10c2a01f2db3397b9fb153fc6b3d8dbbb57f045fd0fcc4.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "41e9056d12f847dedabba2e7c1e1016d1cf1b28ac2a6c1192601b29d78d52b21", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b6c32fee227534384c70abd47a8b9c8ddb3e570fbd524c8ef0e4557c5477184a", "generation_seconds_batch": 13.865917143994011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7564924955368042, "target_z": 1.0312500107478473, "ce": 6.173524379730225, "genuineness": 4.042920112609863, "identity": 0.6515612602233887, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/41e9056d12f847dedabba2e7c1e1016d1cf1b28ac2a6c1192601b29d78d52b21.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "429a54194194e6afdfa022410a3557aa1c7a9fd863eb46869db369502fced47a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "98b4180e8d4a0b5bc438aa23435cca7a49de4f70acd8681b8633739911c07213", "generation_seconds_batch": 20.592719389940612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.719936192035675, "target_z": 0.9609375367218115, "ce": 6.141753673553467, "genuineness": 4.030367851257324, "identity": 0.4699348211288452, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/429a54194194e6afdfa022410a3557aa1c7a9fd863eb46869db369502fced47a.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "42bf0fa93e97dfcf2fcb8fe7263b889db57fa334d9446fd385ba37984d1faa0f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "25419655650a1b0dc2d4f32fba214675dabc76122b57f1872fcbd2ac51dc9f82", "generation_seconds_batch": 19.833576151984744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6224526762962341, "target_z": 0.77343752955658, "ce": 6.205295085906982, "genuineness": 4.394378662109375, "identity": 0.49330663681030273, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/42bf0fa93e97dfcf2fcb8fe7263b889db57fa334d9446fd385ba37984d1faa0f.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "431c075b90649d0e24ed49567ad501e56fb7a2568b77bdc0a1c51d0f80d03685", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f27fb971ffe80af0e656db77195a06d2768d6a90f0feb8eaba3aabab4ee1be8a", "generation_seconds_batch": 15.039467727066949, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1870447397232056, "target_z": 1.8593751379307064, "ce": 6.038498878479004, "genuineness": 4.030367851257324, "identity": 0.5682573318481445, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/431c075b90649d0e24ed49567ad501e56fb7a2568b77bdc0a1c51d0f80d03685.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "434329cc35ef04b3ec6678e8404b1c662920572b40c7c5dfaeb355f5e1822162", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ad11233d646e82174a3ce6afbcd0950a96bc10c6645e537690456ccc6efd085d", "generation_seconds_batch": 20.39134980889503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5818345546722412, "target_z": 0.6953125456783508, "ce": 6.157639026641846, "genuineness": 4.231201171875, "identity": 0.4742971658706665, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/434329cc35ef04b3ec6678e8404b1c662920572b40c7c5dfaeb355f5e1822162.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "47a0132f1d424b5e401abe618a96b43d32079992fe9a026164cdef3d86bd4ecc", "generation_seconds_batch": 17.498938789009117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22084090113639832, "target_z": 0.000976563731524164, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.6745131015777588, "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_Pride/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "heldout-es-3", "language": "es", "sentences": [ "Alguien ha movido la pequeña silla azul.", "Estaba aquí... junto a la estantería alta.", "La colocaremos después de comer." ], "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-3", "key": "43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c", "bucket": "emo_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "686ef7eef64b8afb49f538ad2f9c6a75e7a590ab377b0a5518640cd3e9304700", "generation_seconds_batch": 13.696569747058675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37874388694763184, "target_z": 0.30468751164350116, "ce": 6.372091293334961, "genuineness": 4.570107460021973, "identity": 0.5484272241592407, "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_Pride/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "441bd06c10adcc337c93574b41247fec83f4f8e7578a93ff111595b96c8141ef", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f1cf0d308e438b473258c9cbc7a37cfcfee82b11f13fb8ec1159b34fc2bbcc35", "generation_seconds_batch": 18.83617032004986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48841285705566406, "target_z": 0.5156250483653126, "ce": 6.149696350097656, "genuineness": 4.042920112609863, "identity": 0.6736225485801697, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/441bd06c10adcc337c93574b41247fec83f4f8e7578a93ff111595b96c8141ef.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "442d8fd19455a17f4bd80309a92b048c549646021d64a53568e797fe045695dd", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a2e98ab2bd79850db5a710761a041bd866185022a7109abf2153daf2aa9a2759", "generation_seconds_batch": 16.346996868029237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.081437587738037, "target_z": 1.6562501110610883, "ce": 6.205295085906982, "genuineness": 3.71028995513916, "identity": 0.09932167083024979, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/442d8fd19455a17f4bd80309a92b048c549646021d64a53568e797fe045695dd.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "4447707eb508b07e892e761a7ea7aa7326120a3ac5888567270e4cd1f17cb868", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "dac35790d22bb1b81c8a28cefe59943231d3dc7ba5dcd12532387e066247e5fb", "generation_seconds_batch": 20.171932484023273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5655872821807861, "target_z": 0.6640625062695775, "ce": 6.133810997009277, "genuineness": 3.8671910762786865, "identity": 0.5777769088745117, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4447707eb508b07e892e761a7ea7aa7326120a3ac5888567270e4cd1f17cb868.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "44828d02f2d4934d265c83fafb06c2e689ceb325e0180e859d4983f39598159e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bc6bdd075c599543489fe3d920d63a711fba732a46ec92b6a28a22419779ca9f", "generation_seconds_batch": 18.550568151054904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7300906777381897, "target_z": 0.9804686967085907, "ce": 6.213237762451172, "genuineness": 3.998987913131714, "identity": 0.6281981468200684, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/44828d02f2d4934d265c83fafb06c2e689ceb325e0180e859d4983f39598159e.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "44a1efe23e978431e7ab3d7cd84664aaf9cb211907a22b8bf6e832d44bba5a70", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "978d07be00083ba9950f2511d3eaaf8f7ee2d49f34f178eabd2e15377db1216f", "generation_seconds_batch": 20.171932484023273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.081437587738037, "target_z": 1.6562501110610883, "ce": 6.149696350097656, "genuineness": 3.8797430992126465, "identity": 0.6338558197021484, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/44a1efe23e978431e7ab3d7cd84664aaf9cb211907a22b8bf6e832d44bba5a70.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "44c19968a00cbcd2f898025720df4e886fd92e7b6bcd33e3526e8305d79109b3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "50ae83690caa740723194f6e5c218d3c7f8ec084edd785d56e676edcf2641917", "generation_seconds_batch": 21.867657708004117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7077507376670837, "target_z": 0.9375000071652315, "ce": 6.062326908111572, "genuineness": 3.9173994064331055, "identity": 0.6626554131507874, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/44c19968a00cbcd2f898025720df4e886fd92e7b6bcd33e3526e8305d79109b3.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "456d48630aeb7a67b1f03ea0d9ab2f822d2ea990c4cfb78ac85990cb39a4c775", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "a2e259b2e980c6790e567c0910d62ba59dd6a0feb3ed3c6de617013c0fdb0c10", "generation_seconds_batch": 21.106764405034482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8255432844161987, "target_z": 1.1640624489477256, "ce": 6.0305562019348145, "genuineness": 3.7040140628814697, "identity": 0.34336283802986145, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/456d48630aeb7a67b1f03ea0d9ab2f822d2ea990c4cfb78ac85990cb39a4c775.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "45bc55bd12200c74030ff2e805e808ed431024b6b0034fb175a9582d343a2ea3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "040ba0e890d3963bb670d77a740fd05d5f4035d8749872c84a3b7de8655eeed2", "generation_seconds_batch": 17.11582081799861, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8702232241630554, "target_z": 1.249999942678148, "ce": 6.173524379730225, "genuineness": 4.024092197418213, "identity": 0.18136921525001526, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/45bc55bd12200c74030ff2e805e808ed431024b6b0034fb175a9582d343a2ea3.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "8410511ba7be3c170766d2feaa1b642530f2f9d8314acae00e3a833dbc832a41", "generation_seconds_batch": 13.710121347103268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3495172262191772, "target_z": 2.1718750734436227, "ce": 6.252951145172119, "genuineness": 4.042920112609863, "identity": 0.6120630502700806, "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_Pride/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "4662f9480c81645b1485367c44c48a3628aa4e8393a657783e78ba2f832a119d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4601f8f4d8c5888aea3180a9d6f8c63c4799752a9f1adedea44bf75a0e97d4b2", "generation_seconds_batch": 16.284089324064553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6671326160430908, "target_z": 0.8593750232870023, "ce": 6.260893821716309, "genuineness": 4.218649387359619, "identity": 0.36451423168182373, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4662f9480c81645b1485367c44c48a3628aa4e8393a657783e78ba2f832a119d.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "4681309295dd239987c962d07d61cbdb6d2f1f60be1ca5faa92ec9b92a2257f6", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "422b5412db868ebeef6881f5f55ba13526e78ebf8c03247e5595e0e6beaa4379", "generation_seconds_batch": 19.22178163798526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.771945834159851, "target_z": 2.9843751809220955, "ce": 6.459460258483887, "genuineness": 4.074300289154053, "identity": 0.4617023766040802, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4681309295dd239987c962d07d61cbdb6d2f1f60be1ca5faa92ec9b92a2257f6.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "479a459e8f26b4e0d932599357610c49f6e7a8ac9d55a9955036a79de92df589", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "935c65a0abae3792e62de7115bbe9ab4239a6d04a9a3ab2df2817b22d1d6bf0b", "generation_seconds_batch": 19.66440230398439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42850106954574585, "target_z": 0.40039058536731326, "ce": 6.395919322967529, "genuineness": 4.243753433227539, "identity": 0.37747281789779663, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/479a459e8f26b4e0d932599357610c49f6e7a8ac9d55a9955036a79de92df589.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": "47a3072d74bddf5dcba12f0d3dd89bc525cf39841f324c69022578e7f7fc2765", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8c765f5e47e12c3db9bf550b9adc4b2c604bfade7b37d46598530327cb3ba04a", "generation_seconds_batch": 14.707318197004497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47622740268707275, "target_z": 0.4921875188087327, "ce": 6.1020402908325195, "genuineness": 4.168440818786621, "identity": 0.5057923197746277, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/47a3072d74bddf5dcba12f0d3dd89bc525cf39841f324c69022578e7f7fc2765.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "47cacc79561a1fc28e52bbf1f784ceb6d302c858a54711a53efbe72bd97a0f40", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7e7bc0f801bd1575e08074cfd358279a95b53dc1c0f80e11c2ed14aad71b2207", "generation_seconds_batch": 19.710847083013505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.186250686645508, "target_z": 3.781250039408773, "ce": 6.419747352600098, "genuineness": 4.18726921081543, "identity": 0.4611971974372864, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/47cacc79561a1fc28e52bbf1f784ceb6d302c858a54711a53efbe72bd97a0f40.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "9c2e9334ad05ec82cc8e857152a8365fc4656b0b0224ec4c1d983fa2adcfd989", "generation_seconds_batch": 16.93506950500887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5452781915664673, "target_z": 0.624999957008611, "ce": 6.141753673553467, "genuineness": 4.519899368286133, "identity": 0.7584075331687927, "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_Pride/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "4921887af4bdd70e3e3e019f5369a4d302bbe3983ea8f548c472ec28dd45becf", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "95c1218598f7554cfd165de4aa0eb37b5daee99f161548664b6657a25c6fedd6", "generation_seconds_batch": 14.132867455016822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3982590436935425, "target_z": 2.2656251916699426, "ce": 6.229123115539551, "genuineness": 4.3127899169921875, "identity": 0.390945702791214, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4921887af4bdd70e3e3e019f5369a4d302bbe3983ea8f548c472ec28dd45becf.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "49cf7ba66a246e4b89aa9d0626c92a715f0d81fc794f91e14e1c304ede6b0c79", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e3630f94d6ff04620971e06992abf6a5db4b89bb2c81af74ca79358a2d54bfc5", "generation_seconds_batch": 19.638502226909623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7727397084236145, "target_z": 1.0624999355129165, "ce": 6.38003396987915, "genuineness": 4.331617832183838, "identity": 0.6916300654411316, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/49cf7ba66a246e4b89aa9d0626c92a715f0d81fc794f91e14e1c304ede6b0c79.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb0defb067deef319c4602896378c26373ab59a3461a78428a1b7db39b01df61", "generation_seconds_batch": 14.745023909024894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8296051025390625, "target_z": 1.1718749587999189, "ce": 6.284721851348877, "genuineness": 4.344170093536377, "identity": 0.7145195007324219, "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_Pride/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.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": "49dee0e26cf9c4c33d74b6561f2ae636c99297f8221d25d55eab1b68c849eb8d", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ba2f36cd3b172c5b13f5f4c73d50051e02c4a6b62e9a117218f7b22ceb23394f", "generation_seconds_batch": 22.252622817992233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48841285705566406, "target_z": 0.5156250483653126, "ce": 6.1894097328186035, "genuineness": 4.218649387359619, "identity": 0.7396003603935242, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/49dee0e26cf9c4c33d74b6561f2ae636c99297f8221d25d55eab1b68c849eb8d.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "49fc6def84aaba5cc78e6118569eb127ef665d97b06bf9a6247168339ba5efa7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7d74250b28a9a3c1b228aad14e8b520b5889b53dd878c47b5eb85f586a3c7528", "generation_seconds_batch": 14.946834212983958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9344183206558228, "target_z": 3.296875116435012, "ce": 6.125868320465088, "genuineness": 4.042920112609863, "identity": 0.12818387150764465, "hypothesis": "Die Tür 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_Pride/49fc6def84aaba5cc78e6118569eb127ef665d97b06bf9a6247168339ba5efa7.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "4b37664602753e9924278d2110ccfe9302b6e2f3ed3d53e0d13ce76a688f82f0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "84456b326f9bd1d3a89000dcc910598dca740afafcddb2911620dc1763586b94", "generation_seconds_batch": 13.878058997099288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7016580104827881, "target_z": 0.9257812423869415, "ce": 6.022613525390625, "genuineness": 4.21237325668335, "identity": 0.612193763256073, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4b37664602753e9924278d2110ccfe9302b6e2f3ed3d53e0d13ce76a688f82f0.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "4b6d8d05de089ececb27fa86bf14ee9972d9d8346c9595b34c353992375b0e4d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0ce69875f8a922c0801ed907434a76fbdb78bb8bc524a6a4b850d91559c4607f", "generation_seconds_batch": 21.125492331921123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5534018278121948, "target_z": 0.6406249767129977, "ce": 6.332377910614014, "genuineness": 4.444586753845215, "identity": 0.5231897830963135, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4b6d8d05de089ececb27fa86bf14ee9972d9d8346c9595b34c353992375b0e4d.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": "4bca822257d32985146bd3e0cff7c82e6cac7c8644345b150a12ab22f1792cae", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Your message arrived after I had left.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb6435b0492bea982312cb9e7cc32030abe4e22c0b14ebeeb6fbc1e1283c5fa8", "generation_seconds_batch": 16.340430550975725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7686778903007507, "target_z": 1.0546874256607233, "ce": 6.4912309646606445, "genuineness": 4.017816066741943, "identity": 0.2595164179801941, "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_Pride/4bca822257d32985146bd3e0cff7c82e6cac7c8644345b150a12ab22f1792cae.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "4c080e357cbb57ab86086477717fac2f579c1e58230ded24edbd457df70ce017", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1640aa59c9c9c190d5242f916e49ca2d79c2386d8a087816f0b755877d084d92", "generation_seconds_batch": 21.143317345995456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5038660764694214, "target_z": 2.468749989252153, "ce": 6.308549880981445, "genuineness": 4.231201171875, "identity": 0.4033511281013489, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4c080e357cbb57ab86086477717fac2f579c1e58230ded24edbd457df70ce017.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "4c1cc6349ddc6cd724eb53030c544ac6bd34ffbc24736b10a9fca870097aadb5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a230b8a88abf602be37908fa09470a5be20102d08898b7744420f12f73b90194", "generation_seconds_batch": 20.600227201008238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4488101601600647, "target_z": 0.43945313462827984, "ce": 6.38797664642334, "genuineness": 4.319066047668457, "identity": 0.3456963002681732, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4c1cc6349ddc6cd724eb53030c544ac6bd34ffbc24736b10a9fca870097aadb5.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "4c371fdf37831414e0c9b272f9339eb57aba26e4c4b781aedb8d15b5cad5432f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "84d848d963324f2f9ad2f142be368e4b65fc6352e617bd2ebea0984842e89e87", "generation_seconds_batch": 18.62059354002122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9473977088928223, "target_z": 1.398437515226117, "ce": 6.221180438995361, "genuineness": 4.086852550506592, "identity": 0.24642883241176605, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4c371fdf37831414e0c9b272f9339eb57aba26e4c4b781aedb8d15b5cad5432f.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "4c418b6927b3165736f5a33c2dba8fa2255ca601b39cba9e71f5dc99ff765aa2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "12f813d3d9f81a2e127305da2c569197ac17988bf80361983108d6ecb34734cc", "generation_seconds_batch": 21.76221097598318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3657644987106323, "target_z": 2.2031251128523963, "ce": 6.173524379730225, "genuineness": 4.105680465698242, "identity": 0.5850673913955688, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4c418b6927b3165736f5a33c2dba8fa2255ca601b39cba9e71f5dc99ff765aa2.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "4c7af4996bdc48d3da04eeef21e42db72aac490e5a8bdecf638e53d45c5c68f5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d93a04e1ed547fe46a498f1eba433734415d38ce546f67f3a08a99fbc1225c9f", "generation_seconds_batch": 19.069936497020535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5066909790039062, "target_z": 0.5507812280564786, "ce": 6.173524379730225, "genuineness": 4.375550270080566, "identity": 0.5997700691223145, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4c7af4996bdc48d3da04eeef21e42db72aac490e5a8bdecf638e53d45c5c68f5.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": "4c8f6271feff13f53337a8b592439d7b4a452473b5ff99700317cb6652058372", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Someone moved the little blue chair.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "151e54fdf263dbe654e57dcb2ce6ced2eb9e8bf77bbf986e51be339386db3de0", "generation_seconds_batch": 16.45845761091914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3543730080127716, "target_z": 0.25781250985219334, "ce": 6.467403411865234, "genuineness": 4.13078498840332, "identity": 0.34587597846984863, "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_Pride/4c8f6271feff13f53337a8b592439d7b4a452473b5ff99700317cb6652058372.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "4cbbd0c7ea9a6d24b0d8b57637f7705109123bb4ca92fefdef39d008b80470fb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4241d0de54a15508146330eec4ba7933801c111f2bd017bcaf8ec3fe9a923196", "generation_seconds_batch": 19.710847083013505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1050143241882324, "target_z": 3.624999842364907, "ce": 6.4515180587768555, "genuineness": 4.105680465698242, "identity": 0.4710034132003784, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4cbbd0c7ea9a6d24b0d8b57637f7705109123bb4ca92fefdef39d008b80470fb.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "4d54ab4eee424bccde90157aabb8be15ebd61e9f17c2bd8e762248e71eaa5302", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4ab78d6e3c219a0a3cba3fa9dc72138e4cd4311770caf11b952d6d234a8ad8e2", "generation_seconds_batch": 24.121200083987787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2431159019470215, "target_z": 3.8906247187646636, "ce": 6.125868320465088, "genuineness": 4.105680465698242, "identity": 0.2516358494758606, "hypothesis": "Die Tür 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_Pride/4d54ab4eee424bccde90157aabb8be15ebd61e9f17c2bd8e762248e71eaa5302.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "4dbcb57a44211e7a42a4dc2d177dfa9b74b2eeef326c58e94f9929db7d9ac6bb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 130, "seconds_generated": 10.4, "mp3_sha256": "65a7ada3e50dea3de0571d069eecc17ffeff046faddd8f2a20a8aeadb0ff7173", "generation_seconds_batch": 18.815947970026173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8092960715293884, "target_z": 1.1328125241826563, "ce": 5.186647415161133, "genuineness": 3.9425034523010254, "identity": 0.5188983678817749, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "wer": 0.06666666666666667, "duration_error_s": 0.20000000000000107, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4dbcb57a44211e7a42a4dc2d177dfa9b74b2eeef326c58e94f9929db7d9ac6bb.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": "4dd641d064c7671f20904482987fb08aa958e8aaf8788df9d1635746f63174c5", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2fa1bb9656f9a5d2ac660d42bcc8f484daad61e2d206088de9458a32f720e49", "generation_seconds_batch": 14.84469162800815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1220556497573853, "target_z": 1.7343749802956134, "ce": 6.252951145172119, "genuineness": 4.20609712600708, "identity": 0.5851991772651672, "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_Pride/4dd641d064c7671f20904482987fb08aa958e8aaf8788df9d1635746f63174c5.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "4dd9ed2390a9a7be1ad2980710fbf406fbc49a14ac8c229417c764ed3afb304e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8d21a40fd68bb95eaa3961630e833087e87b467170aa99a22c68ed306af2ca20", "generation_seconds_batch": 19.638502226909623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.991283655166626, "target_z": 3.40625002507831, "ce": 6.181467056274414, "genuineness": 4.218649387359619, "identity": 0.4145140051841736, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4dd9ed2390a9a7be1ad2980710fbf406fbc49a14ac8c229417c764ed3afb304e.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "4e2530b84cd2267fa719cf320e84285b2d5514549cb10133f91a99d13824ad0a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2afab9322adbec07a9dae58274f37bc8761e076646321fed57d0ba7528e15922", "generation_seconds_batch": 20.70100660691969, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4388771057128906, "target_z": 2.3437500609044677, "ce": 6.205295085906982, "genuineness": 4.18099308013916, "identity": 0.2568575441837311, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4e2530b84cd2267fa719cf320e84285b2d5514549cb10133f91a99d13824ad0a.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "4e5588c8ea80b2ee4a6f3f1225418c22e3c74ffa5e7b9235802fbace315610d1", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a0f4dc323dbf292fe253247696a3cf834f9514a9799144734aea1c8eb7891cd8", "generation_seconds_batch": 19.103126816102304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.83772873878479, "target_z": 1.1874999785043054, "ce": 5.685050010681152, "genuineness": 3.722842216491699, "identity": 0.476519376039505, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4e5588c8ea80b2ee4a6f3f1225418c22e3c74ffa5e7b9235802fbace315610d1.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": "4e736f663b64d6dc907dd3525b23068d083a85222f65f18b42b500d1c088c314", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "10d221c42293b7c8e105a84d7bad9eb57c523b7fcad788e3811695a4eaff5fb6", "generation_seconds_batch": 19.34367679199204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6102672219276428, "target_z": 0.75, "ce": 6.141753673553467, "genuineness": 3.923675537109375, "identity": 0.6746041774749756, "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_Pride/4e736f663b64d6dc907dd3525b23068d083a85222f65f18b42b500d1c088c314.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": "4edc93b6bfddf436e99330e52405e6481ea7d13706ea3e30a7463d5aae467b9e", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8fc09edfd8c267d9992ab44bbc3f5fd8381f02569e8943117b7a64b84137f8d4", "generation_seconds_batch": 13.746408510953188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5513709187507629, "target_z": 0.6367187217869009, "ce": 6.157639026641846, "genuineness": 4.143336772918701, "identity": 0.5636457204818726, "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_Pride/4edc93b6bfddf436e99330e52405e6481ea7d13706ea3e30a7463d5aae467b9e.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "4f596c7100c6f3570aa9a16df770a98456c05f9e6a9c44801a90d2c096c1b1f8", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5c6f88c8676901665f49fc5b32e0ac78172cd9ffef4b7cfaff79ee94a418d7ba", "generation_seconds_batch": 21.77159764803946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6915034651756287, "target_z": 0.9062499677564583, "ce": 6.260893821716309, "genuineness": 3.948779582977295, "identity": 0.659782886505127, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4f596c7100c6f3570aa9a16df770a98456c05f9e6a9c44801a90d2c096c1b1f8.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "4f5b73bdb46a67e40a6830f5284405c4a733d741b297d7d7c44fb4c791c20341", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3604a4004d0991e0e1d8de3b7200e78637ba92de12632d580961e15592526d07", "generation_seconds_batch": 21.039873359026387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8523879051208496, "target_z": 5.0624998208692125, "ce": 6.149696350097656, "genuineness": 4.030367851257324, "identity": 0.6182281970977783, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4f5b73bdb46a67e40a6830f5284405c4a733d741b297d7d7c44fb4c791c20341.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": "4f643d2f1212fe1b4bfc2508cf5e9d3acd6cbe07fd78e642ebee7b03ba59d97a", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b5d338aeb803211531ddee017a745a138b810bc73d71f097b955da298598e0d", "generation_seconds_batch": 15.573546422063373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8133578300476074, "target_z": 1.1406249193911457, "ce": 6.205295085906982, "genuineness": 4.243753433227539, "identity": 0.6970824599266052, "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_Pride/4f643d2f1212fe1b4bfc2508cf5e9d3acd6cbe07fd78e642ebee7b03ba59d97a.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "4f8e06a8754a97d0673c53b2d345fbc9297a5bfaf100fdbe3926b33d60f30369", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9fad45b6321f0481cd4606e9406c9fee57338af0a2c578de644cd4bd4b85a62a", "generation_seconds_batch": 14.948380362940952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6411736011505127, "target_z": 4.656249767129976, "ce": 6.3641486167907715, "genuineness": 4.017816066741943, "identity": 0.5861107110977173, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/4f8e06a8754a97d0673c53b2d345fbc9297a5bfaf100fdbe3926b33d60f30369.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": "4f96f979c725237bf16e06d4f01055165c58a75e852b8c46db0c223d9184bf5c", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80b8eaf1fa9e288b0b1d722a086e29aaacfbb9ed8ab42bc22dbcaf43dfbd2cf5", "generation_seconds_batch": 20.069005643948913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7150803804397583, "target_z": 2.875000042991389, "ce": 6.1894097328186035, "genuineness": 4.080576419830322, "identity": 0.6551684141159058, "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_Pride/4f96f979c725237bf16e06d4f01055165c58a75e852b8c46db0c223d9184bf5c.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "500bbc8b8f84432f71f58c22a2f976ae586d804546b76bf0abb584ff39eda7d9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cc3b6b29cc4b27a53c2da9b538d34c4f89f632f766e5ba9b9bec23bb0fea622c", "generation_seconds_batch": 13.736066540004686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6175968647003174, "target_z": 2.6875000358261576, "ce": 5.6334228515625, "genuineness": 3.9801597595214844, "identity": 0.6198968291282654, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/500bbc8b8f84432f71f58c22a2f976ae586d804546b76bf0abb584ff39eda7d9.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "5057d03e4777fc2f35f9a05689d8a060c263781fbc6b1c322d65f51b1cf703f7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f25d3b0a80b96a164e9b8772a8b3d73ed184e42c37a354b13da6887989271b12", "generation_seconds_batch": 20.840067739016376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7280597686767578, "target_z": 0.9765624417824941, "ce": 6.2767791748046875, "genuineness": 4.13078498840332, "identity": 0.5017468929290771, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5057d03e4777fc2f35f9a05689d8a060c263781fbc6b1c322d65f51b1cf703f7.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "5076c4a3f7c108787b44925b113927788f1686e8c25dbd962efa984a23440e4c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "cdfe88b72f8309df8ac0ff5b4fa2aa9da31ec856aa20aa9072711b7c9c45674c", "generation_seconds_batch": 16.563829676015303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.689915418624878, "target_z": 4.749999885356296, "ce": 5.327630043029785, "genuineness": 3.8295347690582275, "identity": 0.47600188851356506, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "wer": 0.06666666666666667, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5076c4a3f7c108787b44925b113927788f1686e8c25dbd962efa984a23440e4c.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "50b8f4209d504c6b660bf4341fad41c92bcd6a5f84a92b533f86a5343d23cfdb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "35dc51e3ff837e76bd52c68f8236c66a207c9672d36e8603a2dc848da4fa1f00", "generation_seconds_batch": 15.039467727066949, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9758303761482239, "target_z": 1.4531249695477662, "ce": 5.919358730316162, "genuineness": 3.8420867919921875, "identity": 0.4645164906978607, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo está.", "wer": 0.13333333333333333, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/50b8f4209d504c6b660bf4341fad41c92bcd6a5f84a92b533f86a5343d23cfdb.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "50bdd166786f636e09136728920053c4be4f1b3aa2c5b387f43c9dbd4116bfa7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a0267659965f3d0907607b327374a238fb358f96ee81346f47e5fddc19f61b0d", "generation_seconds_batch": 13.865472316974774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42139291763305664, "target_z": 0.38671875044782694, "ce": 6.292664527893066, "genuineness": 4.394378662109375, "identity": 0.46173322200775146, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/50bdd166786f636e09136728920053c4be4f1b3aa2c5b387f43c9dbd4116bfa7.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "5152f3d7527892a2e94de36b9b13c5bf4c98b10ee2cfd7a700c846919a6e9e6e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3d2f064ef329bfb5bba4324101fe69b712add83ddf7dc260727bbe70040e637b", "generation_seconds_batch": 21.143317345995456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6825859546661377, "target_z": 2.8125001934612506, "ce": 6.3641486167907715, "genuineness": 4.093128204345703, "identity": 0.4626227617263794, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5152f3d7527892a2e94de36b9b13c5bf4c98b10ee2cfd7a700c846919a6e9e6e.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "5190605311016e6c994acc6fcdfea1549552576b2a609e002c606f5b2f5c554b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "65dbbf8f339af869c4a68a469b9e04bb42295a196c724aae8f7109e32effa56e", "generation_seconds_batch": 18.67501478700433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6508853435516357, "target_z": 0.8281249838782291, "ce": 6.086154937744141, "genuineness": 4.243753433227539, "identity": 0.7199195623397827, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5190605311016e6c994acc6fcdfea1549552576b2a609e002c606f5b2f5c554b.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": "52342e4ed93e09154b79f5b31a67f91f5cad466f43de9759529d1395b4c3b8ea", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "88e80adc71c789fe66428b0676bf35dc3e007ce8a57f124e6520434f94155923", "generation_seconds_batch": 16.69264841498807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30563125014305115, "target_z": 0.16406250626957755, "ce": 6.252951145172119, "genuineness": 4.268857479095459, "identity": 0.6860383749008179, "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_Pride/52342e4ed93e09154b79f5b31a67f91f5cad466f43de9759529d1395b4c3b8ea.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "52ed8c9015fbffb6f9548c2bda81bdf3ecf132e5ee7c3ef997fc00c2bd5d13a6", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2a6e8a1c3cdd1ffa2130fee996782e81c8dd95251a2361cce9df2feb1f6bc6d1", "generation_seconds_batch": 18.827744669979438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.096890687942505, "target_z": 3.6093748226605205, "ce": 6.125868320465088, "genuineness": 4.030367851257324, "identity": 0.13961833715438843, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/52ed8c9015fbffb6f9548c2bda81bdf3ecf132e5ee7c3ef997fc00c2bd5d13a6.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "52ee8c11cb2bd245bd5157ae2f2553c294bc9734a9c14675a9a9af95f9497ea7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "051526857a463ba17cdad2ac441136d662f514ba65a1203c8aad44a8f266477e", "generation_seconds_batch": 18.517378206946887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.22360098361969, "target_z": 1.9296874973130382, "ce": 6.2767791748046875, "genuineness": 4.256305694580078, "identity": 0.35847657918930054, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/52ee8c11cb2bd245bd5157ae2f2553c294bc9734a9c14675a9a9af95f9497ea7.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": "533d408e4f5dcefb5aa387e6e2e12c547b3e30e54c7baeda6fa73e5114396308", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b6942665b01a811b5a3fe57e82965dc5c35145a57ba03b72820d55889e4fcbea", "generation_seconds_batch": 22.398940818035044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41225385665893555, "target_z": 0.369140660602244, "ce": 6.260893821716309, "genuineness": 3.9676074981689453, "identity": 0.5663230419158936, "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_Pride/533d408e4f5dcefb5aa387e6e2e12c547b3e30e54c7baeda6fa73e5114396308.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "5368d3740c6dedac4ad895dfb672df0386c56c7f2cba1cde5e50b44d16654f47", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "89a019defe3220bc5624d4135a3298afc6e94952deca427dfa7e4377123f0fb6", "generation_seconds_batch": 15.548954220954329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5696491003036499, "target_z": 0.6718750161217709, "ce": 6.3641486167907715, "genuineness": 4.218649387359619, "identity": 0.3761407732963562, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5368d3740c6dedac4ad895dfb672df0386c56c7f2cba1cde5e50b44d16654f47.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "5393b1895a8aaba6d61023f9c1da57dde90dce086416ec59bc84c68c5e87bb5c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "38ed518a2404a5deb299bbb0150872e9754f7006a10de7a3fc73b4dea632f6ae", "generation_seconds_batch": 21.187073144013993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6996271014213562, "target_z": 0.9218749874608448, "ce": 5.935244083404541, "genuineness": 3.835810661315918, "identity": 0.47291284799575806, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5393b1895a8aaba6d61023f9c1da57dde90dce086416ec59bc84c68c5e87bb5c.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "53c156916d2666a01f2b4fc5f2462ea5c9c1ed735237116ebcab8cab5f1bfb09", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7c755f19d3e42d645b54ef6a1631f8134b454d07035a79e2f56ea6b684747db6", "generation_seconds_batch": 14.85209869092796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6508853435516357, "target_z": 0.8281249838782291, "ce": 6.324435234069824, "genuineness": 4.344170093536377, "identity": 0.4211525022983551, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/53c156916d2666a01f2b4fc5f2462ea5c9c1ed735237116ebcab8cab5f1bfb09.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "df18628585bda8430fef5a36cdcaecb26c5809c6fc29d2240ec3fea875d9d3ba", "generation_seconds_batch": 13.710121347103268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3332699537277222, "target_z": 2.1406250340348496, "ce": 6.205295085906982, "genuineness": 3.9173994064331055, "identity": 0.35770466923713684, "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_Pride/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.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": "553e878cdf62cc73259f909b32ff169a6b30aaddf4f554a2c032f8172d022a7d", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "378415897c8359bf553e2b332c4d1af9704a9b3d3731786e8434f4aec80e4056", "generation_seconds_batch": 21.867326283012517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.292651891708374, "target_z": 2.0625001648003245, "ce": 6.268836498260498, "genuineness": 4.168440818786621, "identity": 0.540920615196228, "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_Pride/553e878cdf62cc73259f909b32ff169a6b30aaddf4f554a2c032f8172d022a7d.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "55fda379c176633b34d02ab53723ef52cdeb9bf3fc9141cea269d36a5c9c5acf", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "be2d9f22725efa10e83c936fe8458ef8d08ba93cea9501e8a7049ee10102b367", "generation_seconds_batch": 14.22510407899972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1342411041259766, "target_z": 1.7578125098521933, "ce": 6.284721851348877, "genuineness": 4.068024158477783, "identity": 0.11172705888748169, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/55fda379c176633b34d02ab53723ef52cdeb9bf3fc9141cea269d36a5c9c5acf.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "561ede73953ad6549714e254a529ab7b881fccc707ebd2eb231ecdf3f6dbb1e4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "108267501a9a14bbc0bdee3b17edb3b867ad200ec7f9972b87eb8efc29635b55", "generation_seconds_batch": 19.809552451013587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5351237058639526, "target_z": 0.6054687970218318, "ce": 6.117925643920898, "genuineness": 4.193545341491699, "identity": 0.6306259036064148, "hypothesis": "He control todo la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.11764705882352941, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/561ede73953ad6549714e254a529ab7b881fccc707ebd2eb231ecdf3f6dbb1e4.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "5626f3b214da4972c8f86bfc754463c60f1eaaef044c616ca57bc02f5e9f263e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1ef47197982edd86b378020912d1e60f1d5970361c26cc35941b9644ac858f5a", "generation_seconds_batch": 21.106764405034482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0854994058609009, "target_z": 1.6640626209132816, "ce": 6.0305562019348145, "genuineness": 3.9550557136535645, "identity": 0.6233540773391724, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5626f3b214da4972c8f86bfc754463c60f1eaaef044c616ca57bc02f5e9f263e.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "5761351b6b449e1d502a17b9a459e28b787386eacd0deead8aacffb7ff2b9df2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3d3b2c1cc49595cd5ef76bbd5696fdedfd2cb13b8472c1e130768823615d43bb", "generation_seconds_batch": 19.09976040397305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7232040166854858, "target_z": 2.8906250626957757, "ce": 6.054384231567383, "genuineness": 4.15588903427124, "identity": 0.40644243359565735, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5761351b6b449e1d502a17b9a459e28b787386eacd0deead8aacffb7ff2b9df2.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "5776006b5d29f67b6ea3b416dc4d3e4c416bb370e58957a2fb4b00ddcc4d3aca", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e0e224a061e1f637a5f059d9152de78504276dc5b5fc10004c6574be16f17ebd", "generation_seconds_batch": 19.595354238990694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4823201298713684, "target_z": 0.5039062835870226, "ce": 6.24500846862793, "genuineness": 4.419482707977295, "identity": 0.30414122343063354, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5776006b5d29f67b6ea3b416dc4d3e4c416bb370e58957a2fb4b00ddcc4d3aca.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "57c258fb0d50bad173ce13482be5356e1d2fd2ad46328537fe851e498657caf1", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4ea9fec0aa9cc018f2ae812bc5304f9be1119a9f57187ab0046121a3b995ab8d", "generation_seconds_batch": 20.39134980889503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7321215867996216, "target_z": 0.9843749516346874, "ce": 6.165581703186035, "genuineness": 4.093128204345703, "identity": 0.6918447017669678, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/57c258fb0d50bad173ce13482be5356e1d2fd2ad46328537fe851e498657caf1.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": "586586b9d194a0123bd2e62e3c48c4d2568eee62f69049a43d69e73acd12251c", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "36cf9f52b99d2e69a7e98720474b4ea7801813086df0b70b0166d24f59a483e9", "generation_seconds_batch": 16.459236596012488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0895612239837646, "target_z": 1.671875130765475, "ce": 6.1894097328186035, "genuineness": 4.281409740447998, "identity": 0.6622165441513062, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque.", "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_Pride/586586b9d194a0123bd2e62e3c48c4d2568eee62f69049a43d69e73acd12251c.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "5922008563201f0f2b3df6856ce8ae253f1376f799d3da869567d5ebae07a6ce", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "474bfd2fe50a9ac4554f7804d868b85c058098120d56d89c8c5f850599d31797", "generation_seconds_batch": 20.806108572985977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4843510389328003, "target_z": 0.5078125385131194, "ce": 6.205295085906982, "genuineness": 4.375550270080566, "identity": 0.6075320243835449, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5922008563201f0f2b3df6856ce8ae253f1376f799d3da869567d5ebae07a6ce.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "598259b92ceb79987ee5953de2b68eca7a661243a4ea8ff56712506603da5e42", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6313a2af29177020c0e4d775f0dd0160a1d5fd1a0d7a6b54d931ff4a5fab1c6f", "generation_seconds_batch": 18.708674637950025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.048943042755127, "target_z": 1.5937500322435418, "ce": 6.229123115539551, "genuineness": 4.042920112609863, "identity": 0.6178752183914185, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/598259b92ceb79987ee5953de2b68eca7a661243a4ea8ff56712506603da5e42.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "5993a8710a85948cddea3deea27defc41a38b870ee71e2c55e9338b089488af5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "5921c30a9964d10a64378f35f4df3ac0020177ddc26f4abacb36963f447ec8c2", "generation_seconds_batch": 20.57273100502789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1911064386367798, "target_z": 1.8671874184954917, "ce": 6.141753673553467, "genuineness": 4.017816066741943, "identity": 0.7008971571922302, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5993a8710a85948cddea3deea27defc41a38b870ee71e2c55e9338b089488af5.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "5accf4ea11e5f356626aeb3d131e878b6b47ddfb09b9975ad2cdcc9ce4c04756", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3129b03220bdb04f43caeba2c81db1169c75f1fc837312cf371929f3f7095749", "generation_seconds_batch": 13.922116016037762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5371546149253845, "target_z": 0.6093750519479284, "ce": 6.117925643920898, "genuineness": 4.049196243286133, "identity": 0.6779054403305054, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5accf4ea11e5f356626aeb3d131e878b6b47ddfb09b9975ad2cdcc9ce4c04756.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "5b0a8613ace980709adf69af53b75dab6ecf0a805d252425aea0bbd057fd2418", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7852f8b01b7e333b5b96aeee4ed4c2ef459234a6281f30ade97044e2a66f1677", "generation_seconds_batch": 19.452696182997897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9149031639099121, "target_z": 1.3359374364085705, "ce": 6.125868320465088, "genuineness": 3.9550557136535645, "identity": 0.2430836260318756, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5b0a8613ace980709adf69af53b75dab6ecf0a805d252425aea0bbd057fd2418.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "5b93a153a3e12324f3b448a1986ccb69b94a52b43ed5e7aad98579394bcb3d99", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1eb5cba39a0a45712a31ac781b58a9f515df319eeb766349afc7781dcb30f034", "generation_seconds_batch": 15.267406283062883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4417019784450531, "target_z": 0.42578124238694154, "ce": 6.157639026641846, "genuineness": 4.093128204345703, "identity": 0.725520133972168, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5b93a153a3e12324f3b448a1986ccb69b94a52b43ed5e7aad98579394bcb3d99.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "5b9bb060cf1e27380b6e3bf952fae49374de118d11f77a672c8f5e739a487d6a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3ab99a80564ebcdea45202509159910573398bcd61c796978296d508ca1de870", "generation_seconds_batch": 18.83617032004986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.685410737991333, "target_z": 0.8945312029781682, "ce": 6.197352409362793, "genuineness": 4.281409740447998, "identity": 0.7712737917900085, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5b9bb060cf1e27380b6e3bf952fae49374de118d11f77a672c8f5e739a487d6a.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "5bf1ab8b491977d4d1222309de8d5d03f57c1bab53aa3886bbb73040426754c0", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "014f4c4f214ab540764746fac02c672ac7619b5ea54ad1d2665a2affb0395675", "generation_seconds_batch": 17.54473206703551, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7768015265464783, "target_z": 1.0703124453651098, "ce": 6.197352409362793, "genuineness": 4.2751336097717285, "identity": 0.6665874719619751, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5bf1ab8b491977d4d1222309de8d5d03f57c1bab53aa3886bbb73040426754c0.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": "5c01e478496b28eaec608ba5247ee8911d5c42f9b43dcee9c7fec594951ece23", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Someone moved the little blue chair.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1588ab1871edc17152a892f61019ce8bdb0e91d2fc4cc1dee1f1b23e10436a5d", "generation_seconds_batch": 19.438986046006903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3564038872718811, "target_z": 0.261718707456438, "ce": 6.316492557525635, "genuineness": 4.093128204345703, "identity": 0.3140537440776825, "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_Pride/5c01e478496b28eaec608ba5247ee8911d5c42f9b43dcee9c7fec594951ece23.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "5c2da07ec6b45bb88cc7bce3426e85596bfd5227b2bb292f235a1a991752fc6f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fabbcb23a18c149ba0d534ab3fc9a4b0ebda99b356c8d575642a80ca9ff68d94", "generation_seconds_batch": 22.38175440998748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2439100742340088, "target_z": 1.9687500465740047, "ce": 6.252951145172119, "genuineness": 4.300237655639648, "identity": 0.46019262075424194, "hypothesis": "J'ai trouvé la 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_Pride/5c2da07ec6b45bb88cc7bce3426e85596bfd5227b2bb292f235a1a991752fc6f.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "5c35e867c90a3af9c4ed99bb606e81c403200348b10259e465f0e1714b539440", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "aff746641e1f4eecb6fe845114b5d8e9c03ba5108cf001546676a4735fa351a2", "generation_seconds_batch": 15.021931760013103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7524306774139404, "target_z": 1.023437500895654, "ce": 6.221180438995361, "genuineness": 4.074300289154053, "identity": 0.6157202124595642, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5c35e867c90a3af9c4ed99bb606e81c403200348b10259e465f0e1714b539440.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "5d32e69161977fcb2200f07a94231444da5cca3ec8998c1562f59eee603330ce", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ce7cde374620236750656cf26c762855eb1f8d796fae564f934b6c2e852b06a7", "generation_seconds_batch": 20.69968763110228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6508853435516357, "target_z": 0.8281249838782291, "ce": 6.292664527893066, "genuineness": 4.143336772918701, "identity": 0.5370351672172546, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5d32e69161977fcb2200f07a94231444da5cca3ec8998c1562f59eee603330ce.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "5d52806825864e022c7926138f4617650ee9caa05ca29a24cbf6b2bfe402f455", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4d5d99ae439b3d20388884dc1b71f9ba2b711ecff12376602a7b0f76ec664b38", "generation_seconds_batch": 16.29050032107625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1667356491088867, "target_z": 1.8203125886697398, "ce": 6.197352409362793, "genuineness": 3.9927117824554443, "identity": 0.1619044840335846, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5d52806825864e022c7926138f4617650ee9caa05ca29a24cbf6b2bfe402f455.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "5dda591095778f1c245ef272f1bcb1042f4f0116b87bd3b0aa47a6cdec532ac3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d092ecc06f4fcc674df0da0f32bc447ca9c65d28bd5e6223e59756ca620f1fbe", "generation_seconds_batch": 21.474003519047983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8296051025390625, "target_z": 1.1718749587999189, "ce": 6.117925643920898, "genuineness": 4.13078498840332, "identity": 0.6806932687759399, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5dda591095778f1c245ef272f1bcb1042f4f0116b87bd3b0aa47a6cdec532ac3.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "a5af501152ed6e24fdf1a02be0b23452e2300af51a03b53864bd39c262d37140", "generation_seconds_batch": 14.633490712032653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21830226480960846, "target_z": -0.003906254926096656, "ce": 6.141753673553467, "genuineness": 4.582659721374512, "identity": 0.8012758493423462, "hypothesis": "La route tourna à gauche après le pont. Continue jusqu'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_Pride/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "5e44748c7bd618dfa0535f8a3267fe055da2f51eebee21a611c341b6a2131936", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fd439182454751f39a0cd06403a59902b42f72a544045ce963ac95e231e2d899", "generation_seconds_batch": 22.741602568072267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0042630434036255, "target_z": 1.5078124238694153, "ce": 6.2767791748046875, "genuineness": 4.281409740447998, "identity": 0.7310751676559448, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5e44748c7bd618dfa0535f8a3267fe055da2f51eebee21a611c341b6a2131936.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "5ea1c1492f2564566a1b1d2eac31ce97b0aeff6453b62e94484fbbd9e62d3c3c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3fd8cdec477ca046b3fc348f23de3d71d7ecd1c5908fb0040d1199dbe05d9070", "generation_seconds_batch": 19.86886529903859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1139320135116577, "target_z": 1.7187499605912266, "ce": 6.173524379730225, "genuineness": 3.773050308227539, "identity": 0.2482757270336151, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5ea1c1492f2564566a1b1d2eac31ce97b0aeff6453b62e94484fbbd9e62d3c3c.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "5effbc3bb508d348157de5cadd9a6851737bc4e3b2b3dd23fb0a600b5c79f67d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "fc67abc8da62cc4a6582d3d232e812cbeadc1b9ce9bebbb6f6970ff926b40222", "generation_seconds_batch": 13.730438478058204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3576408624649048, "target_z": 2.1875000931480093, "ce": 6.181467056274414, "genuineness": 4.042920112609863, "identity": 0.5524711608886719, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5effbc3bb508d348157de5cadd9a6851737bc4e3b2b3dd23fb0a600b5c79f67d.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "5f37e6726e0dc0780b519b7bd7b5c321a81e2fa7e2c3513cfa05c8c39ed64505", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "52b42ff9a16f77927239355d4ff8ae906843e3c13ba090dd746a7d51036ecdce", "generation_seconds_batch": 21.489514266955666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2918577194213867, "target_z": 3.9843748369909835, "ce": 6.3641486167907715, "genuineness": 4.137060642242432, "identity": 0.6181281805038452, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5f37e6726e0dc0780b519b7bd7b5c321a81e2fa7e2c3513cfa05c8c39ed64505.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "5feecb9f4b6216d4097f4501259c2d59457268049acc9f4911828714530845b5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6c1873fd8710cd454713aa0b5b2c368b9ab4f414c9af0ba047b9dde17936b3f0", "generation_seconds_batch": 20.691561237093993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3251463174819946, "target_z": 2.125000014330463, "ce": 6.117925643920898, "genuineness": 4.093128204345703, "identity": 0.6362688541412354, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/5feecb9f4b6216d4097f4501259c2d59457268049acc9f4911828714530845b5.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "607a158371486ebbf6273a616135f8554206287216c3b426b5b74ecb4c92e848", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "caff0f386af250ea68b549c5346bfc41b7de953cbd29ce377acc6e7171e39113", "generation_seconds_batch": 18.65737639402505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.203291893005371, "target_z": 1.8906249480520716, "ce": 6.181467056274414, "genuineness": 4.193545341491699, "identity": 0.4042905569076538, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/607a158371486ebbf6273a616135f8554206287216c3b426b5b74ecb4c92e848.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "6168c8880be903e2534f1ce1d0f2e903b53ca2b04ecdfcd5fca1a9436d624a11", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d6dbb2df289dceaa2745ba408750d43dcef6245190b104380f0ff7bd18bd3b55", "generation_seconds_batch": 19.185118341003545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6793180704116821, "target_z": 0.8828125528435823, "ce": 5.831989288330078, "genuineness": 4.18099308013916, "identity": 0.5222572684288025, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6168c8880be903e2534f1ce1d0f2e903b53ca2b04ecdfcd5fca1a9436d624a11.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "61f2a8b37be6120d8c17239a1f68280fcc54bd5e461402b44a4ed46abbd27e45", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8d40b8b8db0c3a3d606dea1278f1cc391b2a24c70b02a9f1b333ba36e0dbef37", "generation_seconds_batch": 13.76709956000559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7930487990379333, "target_z": 1.101562484773883, "ce": 5.967014789581299, "genuineness": 3.9801597595214844, "identity": 0.5906738042831421, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/61f2a8b37be6120d8c17239a1f68280fcc54bd5e461402b44a4ed46abbd27e45.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "6264854dafff42466094eae6502fe1c629a66d7633a6fd6e5779884714fbe4f2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "10908c23da39041b84e73b81fe24a62da0f8fb837c8afd6523e5ce69016a894f", "generation_seconds_batch": 22.610170526080765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.023778200149536, "target_z": 3.468750103895857, "ce": 6.435632705688477, "genuineness": 4.068024158477783, "identity": 0.4212868809700012, "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_Pride/6264854dafff42466094eae6502fe1c629a66d7633a6fd6e5779884714fbe4f2.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "6268e713aef8b72baa1a7796913f4a0ef35807bfbd5a19f70a9a87808e4e5b70", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "138c131736a8091daadea3f76ad4de5c00c7699fdf7c48e967e09e6518e16042", "generation_seconds_batch": 18.425076197017916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2276628017425537, "target_z": 1.9375000071652315, "ce": 6.181467056274414, "genuineness": 3.8169827461242676, "identity": 0.40705442428588867, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6268e713aef8b72baa1a7796913f4a0ef35807bfbd5a19f70a9a87808e4e5b70.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "62b7ea3487e673f7d2037bbbe45d3f03b586d90ca7c0e27b9f2ecf15a6cca0d3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2f7210f37ee8d702f88670b462a4358911d99e73cc0aebd1e8714257f88f774f", "generation_seconds_batch": 20.90412747801747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7849251627922058, "target_z": 1.0859374650694964, "ce": 6.205295085906982, "genuineness": 4.011539936065674, "identity": 0.3252350091934204, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/62b7ea3487e673f7d2037bbbe45d3f03b586d90ca7c0e27b9f2ecf15a6cca0d3.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "62c085454a41fcd1042e25e4510f6d67ce7ad5bac16bfd4fdda625961195ad94", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d262a58061486aa9f1327f490187451dbac2036766227fca29a4fe39fc33fbfc", "generation_seconds_batch": 23.497758479905315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3982590436935425, "target_z": 2.2656251916699426, "ce": 6.046441555023193, "genuineness": 3.7918784618377686, "identity": 0.5023748874664307, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/62c085454a41fcd1042e25e4510f6d67ce7ad5bac16bfd4fdda625961195ad94.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "6367c0731b5cd66bbf251b7b4ff21b12da79225fc78b63fff6b0c20b94857627", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8216466c2ceeb9e0c653d7d054676156a213903f49e6bb1d64a579f54a01faa7", "generation_seconds_batch": 18.43778326897882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0798494815826416, "target_z": 5.499999914017222, "ce": 6.300607204437256, "genuineness": 3.7165660858154297, "identity": 0.4019889235496521, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6367c0731b5cd66bbf251b7b4ff21b12da79225fc78b63fff6b0c20b94857627.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "63adc25316de39a22821742dedad71f020258f417fa528634a3ed6db20b7e3b5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "876857fdf9d6185ad799d75920fae9325a23ae85b385d66060d047cf1d22908b", "generation_seconds_batch": 20.525546623044647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9717685580253601, "target_z": 1.4453124596955729, "ce": 6.1894097328186035, "genuineness": 4.074300289154053, "identity": 0.42036309838294983, "hypothesis": "I found the Little Box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/63adc25316de39a22821742dedad71f020258f417fa528634a3ed6db20b7e3b5.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": "63d5fee6904787887f34f223bc5f4ce406275cdbe536e92e19c90a44689b07c9", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Your message arrived after I had left.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97d2c1bfdaefdc7173f4bcc541dd4587d378c38cf2e46e5ccc92918e4f11af79", "generation_seconds_batch": 15.670576137956232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8174196481704712, "target_z": 1.148437429243339, "ce": 6.41180419921875, "genuineness": 4.137060642242432, "identity": 0.31487008929252625, "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_Pride/63d5fee6904787887f34f223bc5f4ce406275cdbe536e92e19c90a44689b07c9.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": "64467586cd1e402148e2867c4191e4091d378a9dbe313463ad2870ca78e1e955", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ff8889b8b2f34acfef4b5f8a6661f934579c7d2ac9eb8f59d7f4fba48938e71c", "generation_seconds_batch": 13.766021937015466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5188764333724976, "target_z": 0.5742187576130585, "ce": 6.133810997009277, "genuineness": 4.055472373962402, "identity": 0.4332960247993469, "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_Pride/64467586cd1e402148e2867c4191e4091d378a9dbe313463ad2870ca78e1e955.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "646fa6652e4aa9e1f6d127a22cd65f186a2cdb9df39b1356542ca9290a469efe", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "acb924aaa1fa7e9303e2987e8184db1be1ce135ef71fcc042280d617ba7eb1f5", "generation_seconds_batch": 19.61363655596506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8986559510231018, "target_z": 1.3046875116435013, "ce": 5.998785495758057, "genuineness": 4.005263805389404, "identity": 0.6269276142120361, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/646fa6652e4aa9e1f6d127a22cd65f186a2cdb9df39b1356542ca9290a469efe.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": "64878037c1f925b880370bfff21392dab775d331cb3e9f413034440dc0d3cff3", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "07b66ff4e108c8127734781640ce73ef27368401a3bdd88ab748841a7da61f43", "generation_seconds_batch": 14.668054795940407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.646823525428772, "target_z": 0.8203124740260358, "ce": 6.149696350097656, "genuineness": 4.250029563903809, "identity": 0.6306276321411133, "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_Pride/64878037c1f925b880370bfff21392dab775d331cb3e9f413034440dc0d3cff3.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "65565301abbb4cce564974b7d3d84d6b6e6de5632fdee3a9c7ba88cd86f99407", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c6a19ffca84a6e5a67ab351a1e768bcd82ee67041b5d73e3fda7261f2a2527cb", "generation_seconds_batch": 14.210173981031403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0002013444900513, "target_z": 1.50000014330463, "ce": 6.1020402908325195, "genuineness": 4.406930446624756, "identity": 0.719814121723175, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/65565301abbb4cce564974b7d3d84d6b6e6de5632fdee3a9c7ba88cd86f99407.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "65cb7485ee7241f22bc69cf78acb7109a03cdfd4af29a07d6e189d2822d10b96", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a635c066b14ce7b404cd7bff8167bde592ad9c7f2b2ecaaafbcf506a5f13bbf9", "generation_seconds_batch": 20.293878283002414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8742850422859192, "target_z": 1.2578124525303414, "ce": 6.165581703186035, "genuineness": 4.093128204345703, "identity": 0.5522923469543457, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/65cb7485ee7241f22bc69cf78acb7109a03cdfd4af29a07d6e189d2822d10b96.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "662fc19b623b39786d1b77a934d4f61133ebfbf3218b3b788befb38662e0e989", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c54a064ff20a3940388f1990bd1c95e9122b2faf8732f08aeb67e0deda4060a8", "generation_seconds_batch": 20.343839989043772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0895612239837646, "target_z": 1.671875130765475, "ce": 6.284721851348877, "genuineness": 4.281409740447998, "identity": 0.5962027311325073, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/662fc19b623b39786d1b77a934d4f61133ebfbf3218b3b788befb38662e0e989.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "66336048ca09ee15f7ea2a8ce398836374d2905533917610bef561d3de494740", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "77b9080b969420a7b30bbd8c244f98a72d8f983aea15dd616f97c6df97e8f6ca", "generation_seconds_batch": 19.50572011305485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.975036382675171, "target_z": 3.374999985669537, "ce": 6.3641486167907715, "genuineness": 4.068024158477783, "identity": 0.3321727514266968, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/66336048ca09ee15f7ea2a8ce398836374d2905533917610bef561d3de494740.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": "6720f2e773e3b1f94e337728164d4e01e3bf395c8eedfed7616e06979aeb150b", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Escribí el número en el sobre.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d40b2841b11bbdfd27d8d553cd79328431c76e6aec2f97c22124da9c11b4b857", "generation_seconds_batch": 17.492623485974036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9506655931472778, "target_z": 3.328125155843785, "ce": 6.332377910614014, "genuineness": 4.250029563903809, "identity": 0.516571044921875, "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_Pride/6720f2e773e3b1f94e337728164d4e01e3bf395c8eedfed7616e06979aeb150b.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "673c45638f7832adaa6a9149c58d14e696ef6dd66eafd395a5f7b9c3df829200", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0440d310af4145e92fbe50b92d2f1632325f5e0a91cad69f86e68d09db2613e9", "generation_seconds_batch": 22.65488299203571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5716800093650818, "target_z": 0.6757812710478676, "ce": 6.046441555023193, "genuineness": 4.356721878051758, "identity": 0.5575480461120605, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "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_Pride/673c45638f7832adaa6a9149c58d14e696ef6dd66eafd395a5f7b9c3df829200.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "67a46b800a5533a4a9076ccdf0fea305e35ef4784b2b8d40b1b246124ecc42bd", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5500c84fd2e60c6d0f2540062d2042464d5faf7961919acfba0ded4679863167", "generation_seconds_batch": 19.13533135910984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43053197860717773, "target_z": 0.4042968402934099, "ce": 6.348263263702393, "genuineness": 4.268857479095459, "identity": 0.458659827709198, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/67a46b800a5533a4a9076ccdf0fea305e35ef4784b2b8d40b1b246124ecc42bd.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "685230ddf1e3900e027576a02a110f07b6bdd1f66d5c9dd2e5257795f6f4b50c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0a9b370be68d0084efbb32a74fc997662c306fc5ea5abf82306fb0ccf4053768", "generation_seconds_batch": 19.50503546500113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3088990449905396, "target_z": 2.09374997492169, "ce": 6.054384231567383, "genuineness": 4.306513786315918, "identity": 0.5645275115966797, "hypothesis": "J'ai trouvé la 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_Pride/685230ddf1e3900e027576a02a110f07b6bdd1f66d5c9dd2e5257795f6f4b50c.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": "68a6ec02d6f92d3dad60f9a1494dcc92189a8dab117d62464bbe3ff8851cf6be", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f4d3d03e8edbcf27fd3342233c4eeb69169cb493a9d51d69430054f5890c757", "generation_seconds_batch": 21.867326283012517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4063825607299805, "target_z": 2.2812499820869214, "ce": 6.205295085906982, "genuineness": 4.080576419830322, "identity": 0.7072305679321289, "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_Pride/68a6ec02d6f92d3dad60f9a1494dcc92189a8dab117d62464bbe3ff8851cf6be.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "68b142ebda89feefae8c1251fa4f86e62442eacc33175893ec91bec77751fe6b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71eef18d2aaf1c29ae662fc70bc1a655f5e6f53261118111ad929821cbf2c7c1", "generation_seconds_batch": 19.696029087994248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1911064386367798, "target_z": 1.8671874184954917, "ce": 6.165581703186035, "genuineness": 4.093128204345703, "identity": 0.8365401029586792, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/68b142ebda89feefae8c1251fa4f86e62442eacc33175893ec91bec77751fe6b.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "692857e5849fb520a8802d32224ebd915fc31e1752776d15b73aefe7aaa5c6b7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a794061f28438b0ba15a144eaf4af37c14bffb7e045ce836df5c5ca196aa4aa1", "generation_seconds_batch": 19.111111787962727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.992077648639679, "target_z": 1.4843750089565393, "ce": 6.23706579208374, "genuineness": 4.13078498840332, "identity": 0.04367136210203171, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/692857e5849fb520a8802d32224ebd915fc31e1752776d15b73aefe7aaa5c6b7.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "69865a477136d94ba8f6dd78d0bd3a094d59f5f65ad6bae18f99538780eecb55", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "71163b5393b7a6ab6ffe01548d757f7a762078e3c84fe2852fb9ca07b77ab7e9", "generation_seconds_batch": 19.62302931700833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6955652832984924, "target_z": 0.9140624776086516, "ce": 5.816103935241699, "genuineness": 4.262581825256348, "identity": 0.6708742380142212, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/69865a477136d94ba8f6dd78d0bd3a094d59f5f65ad6bae18f99538780eecb55.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "698e4e17364e8a91563c71ee007fef9d58f5f729b00a7173b45dc1c1f01cdd66", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3b31e4b984ce60634c67eeb38981ecfc25ad7fed969aef338da67a298d2dff5e", "generation_seconds_batch": 18.57746955100447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.529030978679657, "target_z": 0.5937500322435417, "ce": 6.181467056274414, "genuineness": 4.231201171875, "identity": 0.5230740308761597, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/698e4e17364e8a91563c71ee007fef9d58f5f729b00a7173b45dc1c1f01cdd66.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "69b0c0ee6601da083b8b24c044a7dc1726bf00840225300507dc4dddb4c8f527", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7ba6573c7b3e38154dded4614756d1f34bfb66441a6c13f6144a1718d28da142", "generation_seconds_batch": 14.948270988999866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8613057136535645, "target_z": 3.15625016838294, "ce": 6.332377910614014, "genuineness": 4.3881025314331055, "identity": 0.33943822979927063, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/69b0c0ee6601da083b8b24c044a7dc1726bf00840225300507dc4dddb4c8f527.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": "6a0fbb87091fd424aa9afaf612469f96d3dc563b790e1fa23e03a0bc9d5cbe7c", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7850c6d031f8e1e57c557acd4b0d28743381120ea088a2708d6718cd82f6914b", "generation_seconds_batch": 21.031190215959214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0611284971237183, "target_z": 1.6171875618001217, "ce": 6.24500846862793, "genuineness": 4.149612903594971, "identity": 0.6014953255653381, "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_Pride/6a0fbb87091fd424aa9afaf612469f96d3dc563b790e1fa23e03a0bc9d5cbe7c.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "6a4777907f0f9799b7e9d99ac45a58bbb66e63b68f10f1e3460752a095fbb5f7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c32d46eb0d4aeaa537b157391e9b89d37e2f4493e3974bdaf0575b54d7be19fc", "generation_seconds_batch": 22.508836121996865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.040025472640991, "target_z": 3.50000014330463, "ce": 6.1020402908325195, "genuineness": 3.998987913131714, "identity": 0.4147528111934662, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6a4777907f0f9799b7e9d99ac45a58bbb66e63b68f10f1e3460752a095fbb5f7.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "32954b71b85ade0fee06ba012ac6229e552156d2580f6d9600e2b1a4385f357f", "generation_seconds_batch": 16.352260833024047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0733139514923096, "target_z": 1.6406250913567015, "ce": 6.308549880981445, "genuineness": 3.8797430992126465, "identity": 0.43175774812698364, "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_Pride/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "6aaec6161bd9605e0148a816bdd80ed5b0cb82b2427e2cff87d5f06db2ac8e11", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "11b0d5357111de5edb636a38eef43a66156f85deea4fafebf6fb712d1efeae95", "generation_seconds_batch": 14.424764416995458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5038660764694214, "target_z": 2.468749989252153, "ce": 6.165581703186035, "genuineness": 4.086852550506592, "identity": 0.4279318153858185, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6aaec6161bd9605e0148a816bdd80ed5b0cb82b2427e2cff87d5f06db2ac8e11.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": "6ad63f858f5c8f638632f7e55a1317b7062bacd94127a6f50d3c200f2757c343", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0d7cc433e08c0713f4b225a1b0a277b338e7c0e86b2d435f93c32ac53d6036eb", "generation_seconds_batch": 14.734632453066297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6427617073059082, "target_z": 0.8124999641738425, "ce": 6.292664527893066, "genuineness": 4.1998209953308105, "identity": 0.6923742294311523, "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_Pride/6ad63f858f5c8f638632f7e55a1317b7062bacd94127a6f50d3c200f2757c343.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "6af6080bc83ca60200c5bdef2b25f8f3a700b87e2d010d6fd8e6e5317be4c14a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9832e6bca8364737ad54072ea2fdcea1fbb38aec6fb78555bed7d4ece57d88d8", "generation_seconds_batch": 24.218496663030237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.251239538192749, "target_z": 3.90624973846905, "ce": 6.23706579208374, "genuineness": 4.143336772918701, "identity": 0.5605474710464478, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6af6080bc83ca60200c5bdef2b25f8f3a700b87e2d010d6fd8e6e5317be4c14a.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "6afc89a792c953bbddea34037a53ee36381b60a78c66fdeb37f231dafafd0713", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1f7698a9f702459eb4de2f91ee419bfb9de06a2790b7e673b8dc33ad957157bf", "generation_seconds_batch": 18.928506533964537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6529162526130676, "target_z": 0.8320312388043258, "ce": 5.990842819213867, "genuineness": 3.886019229888916, "identity": 0.5865724086761475, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6afc89a792c953bbddea34037a53ee36381b60a78c66fdeb37f231dafafd0713.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "6b00d6268edf617e0429d342e5b96c1f4420ccc4662b243a0e984325693fcd47", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8c9f00b8df65689caea8e88af26c69206ec6b266dcc2d552a42999ff7fcb99b5", "generation_seconds_batch": 21.34765262308065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9067795276641846, "target_z": 1.3203124167041838, "ce": 5.9431867599487305, "genuineness": 3.8922953605651855, "identity": 0.4754672050476074, "hypothesis": "La porte 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_Pride/6b00d6268edf617e0429d342e5b96c1f4420ccc4662b243a0e984325693fcd47.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "6b22573706fde6eb50046d418fc97d7bf8b49638b55f175891251f82928aa64e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b50f81139834ff81c791fe886413072555a8dd7b5a7c41512ae57ec03c6b9dcd", "generation_seconds_batch": 17.11582081799861, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8702232241630554, "target_z": 1.249999942678148, "ce": 6.1894097328186035, "genuineness": 3.9550557136535645, "identity": 0.4342682361602783, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6b22573706fde6eb50046d418fc97d7bf8b49638b55f175891251f82928aa64e.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "6b3f90c06e8a3bac3cc7e3186e8abffd927bced75bece3fc99be2212c5291876", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4395ab098190d008b4cc16a4a96d1db27c6bbeccaca6a0985da3c398576f6908", "generation_seconds_batch": 20.485461720032617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0692521333694458, "target_z": 1.6328125815045083, "ce": 6.197352409362793, "genuineness": 4.080576419830322, "identity": 0.6360204219818115, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6b3f90c06e8a3bac3cc7e3186e8abffd927bced75bece3fc99be2212c5291876.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "6b7fc993bfbd6d2330f1197b7c4676291a5b3a09cd95f9d9d04e8544422539e1", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "28c02773c13f092b89f6901a647d4db08ce00248c0408ca6422c36289a36e030", "generation_seconds_batch": 19.551696677925065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.589958131313324, "target_z": 0.7109374507390335, "ce": 6.419747352600098, "genuineness": 4.105680465698242, "identity": 0.45306456089019775, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6b7fc993bfbd6d2330f1197b7c4676291a5b3a09cd95f9d9d04e8544422539e1.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "5abfc6a2aa92dc6ac8199152476c7f7793437c4dd6833e142f23c276b0927c37", "generation_seconds_batch": 13.696569747058675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2015472948551178, "target_z": -0.03613280074454207, "ce": 6.268836498260498, "genuineness": 4.557555198669434, "identity": 0.681736946105957, "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_Pride/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "6b9a63b2fa7a5b985e6a29e902fe678e6fff660ce8d7a2d80c484f0aaf4f4633", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "afd4d0d51bbfeae5c15c1e4794a5d314fd244b8a0cba24ea6a5f8e370bd83de3", "generation_seconds_batch": 15.316499407053925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7118125557899475, "target_z": 0.9453125170174248, "ce": 6.252951145172119, "genuineness": 3.998987913131714, "identity": 0.3371320068836212, "hypothesis": "I found the little box. It was beside the old window. We can look inside today.", "wer": 0.0625, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6b9a63b2fa7a5b985e6a29e902fe678e6fff660ce8d7a2d80c484f0aaf4f4633.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "6bce497cefa0836fa284feb40f87e939e72f550569faf41c1930abc4a9adcea0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0738abc6c3861d8ef9e54f51f1237bc996e40b8dfe76a2c5552403abac0fcb67", "generation_seconds_batch": 22.708041613106616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2276628017425537, "target_z": 1.9375000071652315, "ce": 6.125868320465088, "genuineness": 4.024092197418213, "identity": 0.2508244812488556, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6bce497cefa0836fa284feb40f87e939e72f550569faf41c1930abc4a9adcea0.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "6bf5274d2bbe5f6f0ca34ed9f7816ebd44d4116663a50789db28cad6040a9ddc", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3e541893223a20cb60688612b38c66de847153425999b023bc2af65ea70528fe", "generation_seconds_batch": 16.975801111897454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.048943042755127, "target_z": 1.5937500322435418, "ce": 6.070269584655762, "genuineness": 4.394378662109375, "identity": 0.5170987844467163, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6bf5274d2bbe5f6f0ca34ed9f7816ebd44d4116663a50789db28cad6040a9ddc.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "6c013cd4314821b952f54168d3f8dda89e9ae74fc833c39a286698eb1688adb4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6f77c20cfd621020de64eef11f3267693993f05804ead69e974da38c1ad1ecb9", "generation_seconds_batch": 14.948270988999866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3324759006500244, "target_z": 4.062499935512917, "ce": 6.0305562019348145, "genuineness": 4.15588903427124, "identity": 0.2571508288383484, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6c013cd4314821b952f54168d3f8dda89e9ae74fc833c39a286698eb1688adb4.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": "6c0e6356f50f8909c09c531c9bfde689a3aaff514d1e763a164a25c101b75bda", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f26fe7da370e7127a5e0beb27e3a7abbd0c233f5ece28b9fa851c9df94354d6b", "generation_seconds_batch": 16.26609912898857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6508853435516357, "target_z": 0.8281249838782291, "ce": 6.181467056274414, "genuineness": 4.105680465698242, "identity": 0.6308452486991882, "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_Pride/6c0e6356f50f8909c09c531c9bfde689a3aaff514d1e763a164a25c101b75bda.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "6c97053f01ef6645f6b25ee8760f66136aa558db3d6d89798f647e808ad3243d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1106b24c19fa3ae67218685eb475b30346cb024293e1833eadbc106ea9e32533", "generation_seconds_batch": 19.093734476016834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9677067399024963, "target_z": 1.4374999498433796, "ce": 5.736677646636963, "genuineness": 3.7165660858154297, "identity": 0.6862066388130188, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6c97053f01ef6645f6b25ee8760f66136aa558db3d6d89798f647e808ad3243d.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "6d74f6df55425410a58586ed1e7cf8cee0ccb241f1fb672cae20771299192680", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "53ffc1c44c3bc7c3aae0a7b808d2068681f6ad6bcf543247d3381440e6e67939", "generation_seconds_batch": 20.66052721592132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.040025472640991, "target_z": 3.50000014330463, "ce": 6.41180419921875, "genuineness": 4.074300289154053, "identity": 0.5874476432800293, "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_Pride/6d74f6df55425410a58586ed1e7cf8cee0ccb241f1fb672cae20771299192680.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "6dbb72321657f313b1e1e1d68777603fb90609aaf32597b999a42a4e4a95851a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "33b0dce6297ebdcbcdc7a58de66c34fbadfa3e0fbd968b3116ae92a2f786a8a0", "generation_seconds_batch": 18.547573003103025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7313276529312134, "target_z": 2.9062500824001622, "ce": 5.998785495758057, "genuineness": 3.8295347690582275, "identity": 0.5529102683067322, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6dbb72321657f313b1e1e1d68777603fb90609aaf32597b999a42a4e4a95851a.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "6ea00af28c25754d3ff2d68766fbbdd1d0e0f48256dcbb26452c62c731fd461e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f4c32f75b810759921523a313c883b7a94496e0931216ae15dddf23a6ea9dd9d", "generation_seconds_batch": 22.741602568072267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.178921103477478, "target_z": 1.8437501182263198, "ce": 6.332377910614014, "genuineness": 4.457139015197754, "identity": 0.7011474967002869, "hypothesis": "J'ai trouvé la 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_Pride/6ea00af28c25754d3ff2d68766fbbdd1d0e0f48256dcbb26452c62c731fd461e.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "6eaaa103c63fa909825e9af2efb02c69b54b9c9d39cf3514c51173556e6abd2d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2bf3788de297f58a83608b89b5acd105e389a9c5222591023741937da903f094", "generation_seconds_batch": 19.67428855097387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7889869809150696, "target_z": 1.0937499749216897, "ce": 6.1894097328186035, "genuineness": 3.8797430992126465, "identity": 0.6685989499092102, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6eaaa103c63fa909825e9af2efb02c69b54b9c9d39cf3514c51173556e6abd2d.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": "6f0c6e794eb7f814ebcdbe3400ead46fc36e2d765ddb9c7d1d3600430188acea", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c4a35975642c76df19c8939b3416149daffca6a2e278f8a7a79973e9810c8da6", "generation_seconds_batch": 22.758226522011682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6143290400505066, "target_z": 0.7578125098521933, "ce": 6.157639026641846, "genuineness": 4.13078498840332, "identity": 0.44516727328300476, "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_Pride/6f0c6e794eb7f814ebcdbe3400ead46fc36e2d765ddb9c7d1d3600430188acea.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "6f1c2283fc4ceb1ba8f77db404e4d7916203ff7f4d30af71d4feb3edd7a25d62", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a127699a5377899ca4ddb4f33d75bda309cb1b89fcc66e9ff3c3e1762aa94dea", "generation_seconds_batch": 18.574609696050175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6013495922088623, "target_z": 2.6562499964173845, "ce": 6.109982967376709, "genuineness": 3.9676074981689453, "identity": 0.3504232168197632, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6f1c2283fc4ceb1ba8f77db404e4d7916203ff7f4d30af71d4feb3edd7a25d62.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "6fac27a36565a396e4d50925aa7e4cdc5c86d33eb9cb92218e86bd3f328c9a47", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "13bfe99e0e9bb3911734e4d47e2c0a9694ad1e2a3cf27a7fe10e4fed58115b43", "generation_seconds_batch": 18.67501478700433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9839540123939514, "target_z": 1.4687499892521527, "ce": 6.197352409362793, "genuineness": 3.9173994064331055, "identity": 0.5966910123825073, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6fac27a36565a396e4d50925aa7e4cdc5c86d33eb9cb92218e86bd3f328c9a47.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "6fb0512ccdd6c7c9b4b6d425c0a992161e59a348e5fe02489b30d2229b7f7938", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "368acdca5932f1aa93919a6d4d70c6050ad060eae1f4cdc1d8d9b3078735efff", "generation_seconds_batch": 19.73627337499056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.178921103477478, "target_z": 1.8437501182263198, "ce": 6.308549880981445, "genuineness": 4.105680465698242, "identity": 0.7313170433044434, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6fb0512ccdd6c7c9b4b6d425c0a992161e59a348e5fe02489b30d2229b7f7938.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "6fb44cce5c07a5859e03c6232b2f908f5114cf3861ff4bf0cfdda4eb5d611515", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "28f5506167b4c94379dda8ce294a0689df10f07b0fdf40a39245c60e9e19e41c", "generation_seconds_batch": 19.093130009016022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7443070411682129, "target_z": 1.0078124811912672, "ce": 6.260893821716309, "genuineness": 4.18099308013916, "identity": 0.39051148295402527, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/6fb44cce5c07a5859e03c6232b2f908f5114cf3861ff4bf0cfdda4eb5d611515.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "70b068b0bd7520afa1387a0bb0088ff23ee9cdea2717610adad39276d45d8df2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7fbcce968474933060773014d90718d083f19a3ee9e0385865e94a9d9fb24a39", "generation_seconds_batch": 21.77159764803946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5229382514953613, "target_z": 0.5820312674652518, "ce": 6.141753673553467, "genuineness": 4.174716949462891, "identity": 0.5856314897537231, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/70b068b0bd7520afa1387a0bb0088ff23ee9cdea2717610adad39276d45d8df2.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "710cff1c6930db75f578c413fe69ea9385bcbfe22179823bfdf1a71c500932b3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3cbbd80dbcfe6655d2793bb8afd6c22be1f99754d760bafe390b40e31ed07844", "generation_seconds_batch": 19.13533135910984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6305763125419617, "target_z": 0.7890625492609665, "ce": 6.316492557525635, "genuineness": 4.118232727050781, "identity": 0.3583143651485443, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/710cff1c6930db75f578c413fe69ea9385bcbfe22179823bfdf1a71c500932b3.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "71a13328dcff5edf59b2a9a92da66afebf0fbb20d2edff79793fe56e8310167b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "de35f598655f43b37b1f39f8e6415df9fac51dfb3b9e412a20b9f17a9eb932c0", "generation_seconds_batch": 22.90883691003546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5655872821807861, "target_z": 0.6640625062695775, "ce": 6.078212261199951, "genuineness": 4.406930446624756, "identity": 0.743019700050354, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/71a13328dcff5edf59b2a9a92da66afebf0fbb20d2edff79793fe56e8310167b.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": "720a4a2f0b595a28840508d89c3d597426a9ae9ad63ef30db2c51fca1c76a831", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0a66db790dff48db7574f05949f248dbfae7033433725fde204b056d31322f0", "generation_seconds_batch": 14.84469162800815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9595831036567688, "target_z": 1.4218749301389928, "ce": 6.149696350097656, "genuineness": 4.281409740447998, "identity": 0.6858972311019897, "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_Pride/720a4a2f0b595a28840508d89c3d597426a9ae9ad63ef30db2c51fca1c76a831.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "725468e749a7089bfa20a1068ae04f430f1aede34418ed03a7961b69aad0ccdf", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8b68ce2a4fec4c46969c1fb9746a8132e1f54a48ff4b54a7d40c0356b2ba5f65", "generation_seconds_batch": 20.59188482898753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6143290400505066, "target_z": 0.7578125098521933, "ce": 6.173524379730225, "genuineness": 4.595211505889893, "identity": 0.6048067808151245, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/725468e749a7089bfa20a1068ae04f430f1aede34418ed03a7961b69aad0ccdf.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "72c61b5f2880154e2430e837f940f9f44750b47e8e537c612ed02918f438b6f5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "11dd107bb343c4d79a37001a0c28bd96263dd58c551f94c9f5d1dba7101c5868", "generation_seconds_batch": 18.769832844962366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.893800139427185, "target_z": 3.2187500179130786, "ce": 6.356205940246582, "genuineness": 4.030367851257324, "identity": 0.3937152028083801, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/72c61b5f2880154e2430e837f940f9f44750b47e8e537c612ed02918f438b6f5.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "72f2cc183ff21982860d5eda4f88b033f75411d80c862c5ff35a5e18b74fa697", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e5d198afeec5ea7be21ce4e478035ae1888d14d3a299cd916eb75e1fa9105804", "generation_seconds_batch": 21.95960490894504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3738881349563599, "target_z": 2.218750132556783, "ce": 6.2767791748046875, "genuineness": 4.281409740447998, "identity": 0.5450050830841064, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/72f2cc183ff21982860d5eda4f88b033f75411d80c862c5ff35a5e18b74fa697.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "72ffb1960e5ec21b28855b87320e6149f16c82cba045e3ba23bf57dd7cd1899c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "11bebfb68785a31f0f8a52062c0eaba6dbdcbb5b18ac057dd40ea93058e2d0d9", "generation_seconds_batch": 18.65737639402505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8417905569076538, "target_z": 1.1953124883564987, "ce": 6.221180438995361, "genuineness": 4.720732688903809, "identity": 0.7482701539993286, "hypothesis": "J'ai trouvé la petite boîte. Elle était prêt 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_Pride/72ffb1960e5ec21b28855b87320e6149f16c82cba045e3ba23bf57dd7cd1899c.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": "7335592a2876ece35dfa2e48eeb09953f0a138ff1787c360da7bdaed420c773a", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45c6903622df1cbfe4a9675464857b2ee07cdc7af8337bfba8fc06b51aae0cec", "generation_seconds_batch": 15.573546422063373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0002013444900513, "target_z": 1.50000014330463, "ce": 6.332377910614014, "genuineness": 4.174716949462891, "identity": 0.6508191227912903, "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_Pride/7335592a2876ece35dfa2e48eeb09953f0a138ff1787c360da7bdaed420c773a.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "73eba921d9f30fe469ee37d0d4e5d86427cc5231b9a39d16382088fc769e9a0d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "20810fdd0dc24c299d2e1514e7ab0addec3e390b0c989a4e0e9c19ac34d70093", "generation_seconds_batch": 19.3764107770985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.935212254524231, "target_z": 1.374999985669537, "ce": 6.260893821716309, "genuineness": 4.419482707977295, "identity": 0.6902599930763245, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/73eba921d9f30fe469ee37d0d4e5d86427cc5231b9a39d16382088fc769e9a0d.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "73fed26a3e383fb091b29ca55c98a871d08411ae8b72019b0b4584fb0a2cda3b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "374b3d9ff42a6c7081e9898a2d9d021e1329a7324bd19f2516e3500c41a86b83", "generation_seconds_batch": 19.421157025033608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8905323147773743, "target_z": 1.2890624919391145, "ce": 6.078212261199951, "genuineness": 3.9676074981689453, "identity": 0.5515553951263428, "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_Pride/73fed26a3e383fb091b29ca55c98a871d08411ae8b72019b0b4584fb0a2cda3b.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "741d72a2b3f6f804c7e788f8779515089661dc36662dc44b41a8f3ddda842bd8", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7f2c062c5e80f3ad3baa86c2a9bbcad2d552c8d0045e6bf73492685021cabcf2", "generation_seconds_batch": 23.667363267042674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9506655931472778, "target_z": 3.328125155843785, "ce": 6.0146708488464355, "genuineness": 4.055472373962402, "identity": 0.7661271691322327, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/741d72a2b3f6f804c7e788f8779515089661dc36662dc44b41a8f3ddda842bd8.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": "744b8fa5633c7f3202418a609eeb07d520a7fe068117448e3e58f05b69e99da1", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8a6a31bf131e8bc840ccca68fbc5f25a7f427652dbdef3edc7c697690548b4ff", "generation_seconds_batch": 14.752807327080518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4345937967300415, "target_z": 0.41210935014560324, "ce": 6.197352409362793, "genuineness": 4.18099308013916, "identity": 0.5450447797775269, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/744b8fa5633c7f3202418a609eeb07d520a7fe068117448e3e58f05b69e99da1.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": "7527b3d119fbbd8f0571f95d47acb6d55cf193e291c1a9b1dbfd1e814050fbfe", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ee3510cb87b14be53669f3c6d9e449aa87aa7e3b79a19044f3abd78c79319bc", "generation_seconds_batch": 19.165313865989447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9433358907699585, "target_z": 1.3906250053739235, "ce": 6.324435234069824, "genuineness": 4.162164688110352, "identity": 0.5658367276191711, "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_Pride/7527b3d119fbbd8f0571f95d47acb6d55cf193e291c1a9b1dbfd1e814050fbfe.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "7529bd7769603242e4d1d7707f6e101160a551ece7e3a2545401a21dee77bc80", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "77b49e50a11f8b51f4517f4d186e466f53af5cadab1dba8526c5a592fbeb0269", "generation_seconds_batch": 22.64016802003607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.081437587738037, "target_z": 1.6562501110610883, "ce": 6.125868320465088, "genuineness": 4.381826400756836, "identity": 0.4333721399307251, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7529bd7769603242e4d1d7707f6e101160a551ece7e3a2545401a21dee77bc80.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": "752c9025ca3efa9a9c05b4af2e6d39b5a226c5a9baa6b154f6ca573307301c74", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1a9aab4e743c8a23164114c93d3a0ab4eb422a5388587daa084df5283e303d8", "generation_seconds_batch": 15.382408762932755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5201133489608765, "target_z": 2.500000028660926, "ce": 6.41180419921875, "genuineness": 4.118232727050781, "identity": 0.5085335373878479, "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_Pride/752c9025ca3efa9a9c05b4af2e6d39b5a226c5a9baa6b154f6ca573307301c74.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "7609d822163b29290ae9b96479d6585908cc1efe4f3da788407bb86ddcfc15ea", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "af0c3ded560543ea33c94d61843f03d94fcb64b9103b66ee5fa3c58f3c174630", "generation_seconds_batch": 21.478763755992986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.040025472640991, "target_z": 3.50000014330463, "ce": 6.24500846862793, "genuineness": 4.3127899169921875, "identity": 0.44041600823402405, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7609d822163b29290ae9b96479d6585908cc1efe4f3da788407bb86ddcfc15ea.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": "766965cafe6fff26d38e758210b38054e2dd6b5065d57c08244b2207c19901e5", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6dd34c6b9a937ef5c3445a154ca17b3a35f611446fdc96ff80c4fe4afd0e6456", "generation_seconds_batch": 13.809268933022395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3919447660446167, "target_z": 0.33007811134127746, "ce": 6.157639026641846, "genuineness": 4.281409740447998, "identity": 0.3783201575279236, "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_Pride/766965cafe6fff26d38e758210b38054e2dd6b5065d57c08244b2207c19901e5.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "76917ee471a4fd18c1d5fdf3cfe3179dbbcc5161e44213f242c7077fc5b5d390", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8e67ddee9f6f77ff821f4d7521f94b5843c614893c0e92fa666ebcfad5dbf060", "generation_seconds_batch": 22.189591214992106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0205103158950806, "target_z": 1.5390624632781886, "ce": 6.062326908111572, "genuineness": 4.15588903427124, "identity": 0.7635098695755005, "hypothesis": "La porte 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_Pride/76917ee471a4fd18c1d5fdf3cfe3179dbbcc5161e44213f242c7077fc5b5d390.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "771404b007c9ed4a2863fb73b3289705fe50f1f322bc7167ced5b4ef5afe3743", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "115c9c73d9e3ca76ebf7fe151319544ba170243eb11a8d56fb36040780593cfb", "generation_seconds_batch": 19.7708992670523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5432472825050354, "target_z": 0.6210937020825144, "ce": 6.316492557525635, "genuineness": 4.093128204345703, "identity": 0.408477783203125, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/771404b007c9ed4a2863fb73b3289705fe50f1f322bc7167ced5b4ef5afe3743.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "77363d290685c0df238661e3339b2c0fca9686cc67616d1b89154a13e9443e60", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a430e076324f27fe16f3997ca951e2da3be15196ed9d5a27ebb894a0e3414bd9", "generation_seconds_batch": 14.189467989956029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1537561416625977, "target_z": 3.718749960591227, "ce": 6.070269584655762, "genuineness": 4.017816066741943, "identity": 0.36035582423210144, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/77363d290685c0df238661e3339b2c0fca9686cc67616d1b89154a13e9443e60.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": "7792a1e870fb0c016ce35b3b66a3274ab0523b033ad47dc60e03d107ed42e1b9", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The road turns left behind the bridge.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "949c82311aaa2b92d9addaf19e962d89e51653e92466f83c9354fee7b70b133d", "generation_seconds_batch": 18.435051930951886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.955521285533905, "target_z": 1.4140624202867995, "ce": 6.348263263702393, "genuineness": 3.5471129417419434, "identity": 0.11714821308851242, "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_Pride/7792a1e870fb0c016ce35b3b66a3274ab0523b033ad47dc60e03d107ed42e1b9.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "e4753e228e92d57fefa541027ec78c980849d5b925440ace43b67020745007c7", "generation_seconds_batch": 16.93506950500887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3635120987892151, "target_z": 0.2753906570196283, "ce": 6.23706579208374, "genuineness": 4.595211505889893, "identity": 0.7542974948883057, "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_Pride/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.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": "77d4dde2e26540bfa4601949653d18ffb32f3a347508460327168723e9bef869", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The keys are on the kitchen table.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c1454aa5b1199fd747e7e4afe56897b4698cf91c688cf4bad1a09babea454a9", "generation_seconds_batch": 15.303234120947309, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5574636459350586, "target_z": 0.648437486565191, "ce": 6.348263263702393, "genuineness": 3.9425034523010254, "identity": 0.34920817613601685, "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_Pride/77d4dde2e26540bfa4601949653d18ffb32f3a347508460327168723e9bef869.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "7800e46bbbe06086015f7aead530a7332c76f09b10ea0ce5370140c7c3ae6ef6", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1e89101ce5d096faa2333e8add2736a3b77e3fb04103b1ebb575e427bb7ff67b", "generation_seconds_batch": 18.54594405600801, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7768015265464783, "target_z": 1.0703124453651098, "ce": 6.252951145172119, "genuineness": 4.042920112609863, "identity": 0.13739266991615295, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7800e46bbbe06086015f7aead530a7332c76f09b10ea0ce5370140c7c3ae6ef6.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": "78412692a1c416c0e2ed429bdde76df21dcff4d760c2c9ad2a5a983290bbdda6", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d41095ef9e26b1367e9b36aba3243d77c03e828e91ee03ab6b3aec40d7dc0075", "generation_seconds_batch": 21.844082860974595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0473549365997314, "target_z": 5.4374998351996755, "ce": 6.09409761428833, "genuineness": 4.099404335021973, "identity": 0.6298381090164185, "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_Pride/78412692a1c416c0e2ed429bdde76df21dcff4d760c2c9ad2a5a983290bbdda6.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "785482a794500730bb3e29137d85e36bcfea0f2bd964e9e9af6a99b0090d498d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "79a2229751a95332eeccf8d87e703b83544e7dce5730c1dba1422c8515bbc071", "generation_seconds_batch": 19.111111787962727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9717685580253601, "target_z": 1.4453124596955729, "ce": 6.24500846862793, "genuineness": 4.099404335021973, "identity": 0.28740793466567993, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/785482a794500730bb3e29137d85e36bcfea0f2bd964e9e9af6a99b0090d498d.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "785ff65cac91471de2cde9cd0fd8cac6ef6119c9a2a8023c205b13794e5a4e92", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e07e66a19452123c14d31b1a502b7e4215d87ee28eb53eb5a65f9433b4a07e83", "generation_seconds_batch": 15.289980945992284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6021435856819153, "target_z": 0.7343749802956133, "ce": 6.141753673553467, "genuineness": 4.068024158477783, "identity": 0.7709725499153137, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/785ff65cac91471de2cde9cd0fd8cac6ef6119c9a2a8023c205b13794e5a4e92.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "787f994460787efba664bf17428d4f4da02c378f2ede0d0e4ab69855b254fbc2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ad48c60a2ce16e842fdc863592a6cb734a431d6a4afb9a683b95279d827f42c8", "generation_seconds_batch": 14.21336897497531, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3812177181243896, "target_z": 4.156250053739236, "ce": 6.427689552307129, "genuineness": 4.068024158477783, "identity": 0.6400008201599121, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/787f994460787efba664bf17428d4f4da02c378f2ede0d0e4ab69855b254fbc2.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "78d6b862733c72233e7947aeaae3083b2e92049dfde3c18a76d00084a4fa0614", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cef7c4fcabf79b4389c70f614594bdf5ad2f4f01d22aa39438361ca4cb7d5f1f", "generation_seconds_batch": 14.166461859014817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.894594132900238, "target_z": 1.2968750017913078, "ce": 6.324435234069824, "genuineness": 4.218649387359619, "identity": 0.6004387140274048, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/78d6b862733c72233e7947aeaae3083b2e92049dfde3c18a76d00084a4fa0614.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "78f28e0ea5c7764daf949ab479d4cb1ba6ae6b300faf4ac60589da1613c47d5f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a682c2f79588f97b78197fdc0886d0f0ba0c3018c308d12aaea118dece7b443d", "generation_seconds_batch": 19.593828320037574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9433358907699585, "target_z": 1.3906250053739235, "ce": 5.959072113037109, "genuineness": 3.9676074981689453, "identity": 0.3928797245025635, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/78f28e0ea5c7764daf949ab479d4cb1ba6ae6b300faf4ac60589da1613c47d5f.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "79084ec992c63c53639db156ac39cb5060e85175bb97fd2647b87f1bb9cfa005", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "545a8825e5e5b8fbe1a286159b2eeb736296a05786beb09ba8222ee237bd7629", "generation_seconds_batch": 14.225608340930194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9344183206558228, "target_z": 3.296875116435012, "ce": 5.855817794799805, "genuineness": 4.074300289154053, "identity": 0.4031822681427002, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/79084ec992c63c53639db156ac39cb5060e85175bb97fd2647b87f1bb9cfa005.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "794635b39ac69b629a1e9a5ab27e8af7501736e1ce8ff9c637f417679afc23a4", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bdef0cf324721a606bbf45a01ad6734c870bd8f415022c9265d79a9eeaf8ba26", "generation_seconds_batch": 15.113008160958998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.589958131313324, "target_z": 0.7109374507390335, "ce": 5.855817794799805, "genuineness": 3.9425034523010254, "identity": 0.4205749034881592, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lenta.", "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_Pride/794635b39ac69b629a1e9a5ab27e8af7501736e1ce8ff9c637f417679afc23a4.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "e330d177724e88e2b8a7764f389c6c2e5e823dfbb9d5bb2f6e88de04438e2de9", "generation_seconds_batch": 16.57901625998784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2639976739883423, "target_z": 0.08398439492830011, "ce": 6.117925643920898, "genuineness": 4.356721878051758, "identity": 0.5349054932594299, "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_Pride/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "79baaad4d9897deb6fbcfe08da2765485746d4df78a543f1574c506831c2806e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "380964f7f78bc74715ac8ac32b93a8b35c535556dd73c05c69f466a417777b7e", "generation_seconds_batch": 18.85738208401017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9067795276641846, "target_z": 1.3203124167041838, "ce": 5.895530700683594, "genuineness": 4.105680465698242, "identity": 0.6472460031509399, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/79baaad4d9897deb6fbcfe08da2765485746d4df78a543f1574c506831c2806e.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": "79c29b2c1d8af589d561d37a8baddcaae4e00df3a15cdcdc5a315647355aa179", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e8e0bdb76e17f62f21569158d5906bb6a1e077ce87bc29b915b4ece915cc27e", "generation_seconds_batch": 19.165313865989447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3576408624649048, "target_z": 2.1875000931480093, "ce": 6.348263263702393, "genuineness": 3.8922953605651855, "identity": 0.5516682267189026, "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_Pride/79c29b2c1d8af589d561d37a8baddcaae4e00df3a15cdcdc5a315647355aa179.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "79d8130c4f399d904754ec96a3bb455e69d8ee840a289b00a3f48f75c85c85bf", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b1c90a31073e3697a7e8c20a7a6825249ea168af0e8f0b7719a79bc1000291c2", "generation_seconds_batch": 18.577165237045847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7881929874420166, "target_z": 3.0156249910434605, "ce": 6.38003396987915, "genuineness": 4.143336772918701, "identity": 0.6663116216659546, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/79d8130c4f399d904754ec96a3bb455e69d8ee840a289b00a3f48f75c85c85bf.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "7a6b7f5c63d293344f876d95e6556bd385ca5fbf72a7877f896cebdb89c550f4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "41526f5645ec841338e08a58eacecef0ff6a52d4d26077917aa00ef899b7d896", "generation_seconds_batch": 19.485182320931926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3820117712020874, "target_z": 2.2343751522611695, "ce": 6.046441555023193, "genuineness": 3.8420867919921875, "identity": 0.33566510677337646, "hypothesis": "The 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_Pride/7a6b7f5c63d293344f876d95e6556bd385ca5fbf72a7877f896cebdb89c550f4.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "7a8fbd7672aaf5012c42e379be4e17442bdb5f6a1f3ca6c84c9e96fd28a3d058", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "40a44bf294d18c6e4eacb779a7fd99b0b081764ebd30d25cf8dbcebfe8b0b156", "generation_seconds_batch": 21.732327883015387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.511195659637451, "target_z": 4.406249910434607, "ce": 6.356205940246582, "genuineness": 3.9550557136535645, "identity": 0.49955350160598755, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7a8fbd7672aaf5012c42e379be4e17442bdb5f6a1f3ca6c84c9e96fd28a3d058.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": "7b17b1d45752170f783537ec30ffaca4226553dfe00974008ef47892e140fecc", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c77d2e7ed3c1a24a4a788ce433ae403880b654f2d75ac37a695d85373c4ab57", "generation_seconds_batch": 16.79895474901423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3614811897277832, "target_z": 0.2714844020935316, "ce": 6.332377910614014, "genuineness": 4.444586753845215, "identity": 0.6134194135665894, "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_Pride/7b17b1d45752170f783537ec30ffaca4226553dfe00974008ef47892e140fecc.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "7b693f009f5451231e1200321da7cd40b94d409849ff45508439775a2acaca87", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6a381afb43169a0f9cf03446394158da5f0894540f9728043faeb0343a5e6d16", "generation_seconds_batch": 18.43912618502509, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8905323147773743, "target_z": 1.2890624919391145, "ce": 6.284721851348877, "genuineness": 4.319066047668457, "identity": 0.3763992190361023, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7b693f009f5451231e1200321da7cd40b94d409849ff45508439775a2acaca87.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "7c346fc6ac372763cd0a513d8ea9f89615de2fc4ba24d7073013411298d6f62c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "da5aac499dff19ced70d3e62b54d82bb7b438356c1ec8f17bf451bb08822a94d", "generation_seconds_batch": 19.573647512006573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20002411305904388, "target_z": -0.03906249193911456, "ce": 6.157639026641846, "genuineness": 4.281409740447998, "identity": 0.651699423789978, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7c346fc6ac372763cd0a513d8ea9f89615de2fc4ba24d7073013411298d6f62c.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "7ca4f913e4a010b02e25923616cb792ee1625e922dc73284b01a87f502efebfe", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f239bcc076353a7b37e69700eb8115d858d59a19ff7bcbd32486ba069b00e242", "generation_seconds_batch": 20.592719389940612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45693379640579224, "target_z": 0.45507815433266646, "ce": 6.229123115539551, "genuineness": 4.344170093536377, "identity": 0.7296676635742188, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7ca4f913e4a010b02e25923616cb792ee1625e922dc73284b01a87f502efebfe.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "7cac15b426ea12c2c20fc74e58e15113ea23cfbc505c10b75c091eb273a6aab4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "5a82bf67ebea42a903264dbcb42800ccd5f747b2671a833f387ce9a65518da14", "generation_seconds_batch": 18.815947970026173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5599374771118164, "target_z": 4.500000028660926, "ce": 5.764476776123047, "genuineness": 3.8169827461242676, "identity": 0.2166483849287033, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás, Linda.", "wer": 0.06666666666666667, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7cac15b426ea12c2c20fc74e58e15113ea23cfbc505c10b75c091eb273a6aab4.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": "7d3cd12dabbfcd3721bfb594c8ef8f9251f388703254cca817f466a24cf78545", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "076073b5b5c64b9d726df7c7da8077a289b7a1fdd9d3856079ec6187a6b5c15d", "generation_seconds_batch": 16.69264841498807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.212209552526474, "target_z": -0.015624991043460625, "ce": 6.157639026641846, "genuineness": 4.325342178344727, "identity": 0.7241410613059998, "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_Pride/7d3cd12dabbfcd3721bfb594c8ef8f9251f388703254cca817f466a24cf78545.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": "7d5d023aca262d29afc82accc4e8277d96f69e3e2bd4105afd5ef51c28a28a4f", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The keys are on the kitchen table.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4073bb2b3b3401109a6e1e4b5f4f9df736b6ee0e2df590e1e67b9bc78366bf8", "generation_seconds_batch": 15.303234120947309, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5412163734436035, "target_z": 0.6171874471564177, "ce": 6.292664527893066, "genuineness": 3.9425034523010254, "identity": 0.2648824453353882, "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_Pride/7d5d023aca262d29afc82accc4e8277d96f69e3e2bd4105afd5ef51c28a28a4f.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": "7d673457a1ae2a9714f144174bc2a48029a8458fdc075b4d4ddebeb76292643f", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a6eca2ec79f0d509b8af32d72a06bae6f7ad138dd17d8bc318eba4c269ccfd3c", "generation_seconds_batch": 22.60464243509341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9067795276641846, "target_z": 1.3203124167041838, "ce": 6.181467056274414, "genuineness": 4.13078498840332, "identity": 0.6938268542289734, "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_Pride/7d673457a1ae2a9714f144174bc2a48029a8458fdc075b4d4ddebeb76292643f.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "7dcafaf198cfd1804c27127b4b6d9d049516b00a3c9e0f8026604df411702e82", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c1a2d50dd8f6d0376c7d57d9fa7c78ff4e6d839a1d78e2eefd074c79aba5bc01", "generation_seconds_batch": 18.617735657957383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6305763125419617, "target_z": 0.7890625492609665, "ce": 6.395919322967529, "genuineness": 4.250029563903809, "identity": 0.37743979692459106, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7dcafaf198cfd1804c27127b4b6d9d049516b00a3c9e0f8026604df411702e82.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "7dd2f3c3beb89784db38865cf962b983cf1e6f613564bfc204caf4fed3002c10", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "557c51e2f89f09610219d3de056687836b7af4ed6b5e8f2b868586c117b4833c", "generation_seconds_batch": 19.09976040397305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1301792860031128, "target_z": 1.75, "ce": 6.141753673553467, "genuineness": 4.2751336097717285, "identity": 0.03659564629197121, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7dd2f3c3beb89784db38865cf962b983cf1e6f613564bfc204caf4fed3002c10.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": "7e49d6c2f7c74e4067ee53e808988a22e8e569a94725a34f2c547e016d6e1550", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b53716731494ad2399a713e3c9960c6406383712fdd04cb6842982e65808ff5e", "generation_seconds_batch": 16.2076419449877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5066909790039062, "target_z": 0.5507812280564786, "ce": 6.340320587158203, "genuineness": 4.080576419830322, "identity": 0.6867052912712097, "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_Pride/7e49d6c2f7c74e4067ee53e808988a22e8e569a94725a34f2c547e016d6e1550.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "7e4e148a34b381e3396d7587a2754f9b3535f7c1a61ff20d413cfa20783da27c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "70211be849164795b5957f4c15b4d80d16134169e5d7670f6d2d0ee049d1416f", "generation_seconds_batch": 18.574098577955738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5046600699424744, "target_z": 0.5468749731303819, "ce": 6.3641486167907715, "genuineness": 4.406930446624756, "identity": 0.3166291415691376, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7e4e148a34b381e3396d7587a2754f9b3535f7c1a61ff20d413cfa20783da27c.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": "7ea284471292bdd4c2ab0ababf2b50c55e01b33ea33e19ecb14c2887ca2d2f92", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1ece3a8d5d5ad84225603252555723aecf127ca467f11c7291c85d6de44c2be8", "generation_seconds_batch": 13.839385398081504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.203291893005371, "target_z": 1.8906249480520716, "ce": 6.1894097328186035, "genuineness": 4.118232727050781, "identity": 0.4170020520687103, "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_Pride/7ea284471292bdd4c2ab0ababf2b50c55e01b33ea33e19ecb14c2887ca2d2f92.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "033f452d84daee26e4dabe82c696af703f4f2279368bada0b09b452440bc5d73", "generation_seconds_batch": 14.189587521017529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44779470562934875, "target_z": 0.4375000071652315, "ce": 6.372091293334961, "genuineness": 4.381826400756836, "identity": 0.3177495300769806, "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_Pride/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "7f9e0b4f2a822afa36ee5cdf716d81e50634bbcbdebc6ea34eac9c76f87c8f4e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1c04327075a14b2b65db6921ff99ac0ecf351615b297903f226c8feee590fee9", "generation_seconds_batch": 23.682215058943257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7402452230453491, "target_z": 0.999999971339074, "ce": 6.141753673553467, "genuineness": 4.457139015197754, "identity": 0.6389240622520447, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7f9e0b4f2a822afa36ee5cdf716d81e50634bbcbdebc6ea34eac9c76f87c8f4e.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "7fd5e70571ce07a511ab38a746f724530ccbc20ab0289da5f159780bcc01e1a2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d3f76a6db55d9c7a78daeb09f9ee2cebec995edd5448eae1cfbd534a54dfb959", "generation_seconds_batch": 20.505787793081254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0773757696151733, "target_z": 1.6484376012088948, "ce": 6.268836498260498, "genuineness": 3.785602569580078, "identity": 0.22394774854183197, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7fd5e70571ce07a511ab38a746f724530ccbc20ab0289da5f159780bcc01e1a2.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "7fd820cb443a1ad4ace5f946bc0effbb99db0ebf16a3e4d9e97b029f4bced948", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "650e80551ac2e9c3d88715ff5f9d17ebd32e279a4d3ffd9063b728aae4f77492", "generation_seconds_batch": 22.167867842013948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9433358907699585, "target_z": 1.3906250053739235, "ce": 6.006728172302246, "genuineness": 3.9550557136535645, "identity": 0.6387402415275574, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7fd820cb443a1ad4ace5f946bc0effbb99db0ebf16a3e4d9e97b029f4bced948.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "7fec37c2b6b26a2b28d822fa43305a4e7a934d0ea682653a7e6723198831b11e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "201cb26fa42933a1116e509530f3aa4d2a25514ee1a0a1e1ae985853de5a042e", "generation_seconds_batch": 15.289980945992284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45490288734436035, "target_z": 0.4511718994065698, "ce": 6.046441555023193, "genuineness": 3.986435890197754, "identity": 0.6890418529510498, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/7fec37c2b6b26a2b28d822fa43305a4e7a934d0ea682653a7e6723198831b11e.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "803539ecff84fa5da3614a6777d3bc46d04000dfdfbeeaaccf6513a85dbef1d7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "251d79e22a775c442456ea9b5d81e70603dc375a5f3137abc3f7ba3893696a3b", "generation_seconds_batch": 20.869212412973866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4224083721637726, "target_z": 0.3886718779108753, "ce": 6.348263263702393, "genuineness": 4.457139015197754, "identity": 0.6330151557922363, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/803539ecff84fa5da3614a6777d3bc46d04000dfdfbeeaaccf6513a85dbef1d7.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "80632093b565ef157b11c8cb440fb7116a17b786b6fc58d9dbdfce06cbbaa6fa", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "182567638b434a72706f6c6ecfc1710f8b72253a07be12f787883277001ff5dc", "generation_seconds_batch": 21.125492331921123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5554327368736267, "target_z": 0.6445312316390943, "ce": 6.038498878479004, "genuineness": 4.030367851257324, "identity": 0.5490406155586243, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/80632093b565ef157b11c8cb440fb7116a17b786b6fc58d9dbdfce06cbbaa6fa.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "80ad41eba03a33f11140e24a7abe9b72fce1d48d0a6bb104f870bba98afc2e70", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "14c83a3fe3ec374cfadd7ebde34d5545823a4ae99a060b38face7078ac9d827f", "generation_seconds_batch": 19.460940657998435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7524306774139404, "target_z": 1.023437500895654, "ce": 6.086154937744141, "genuineness": 4.356721878051758, "identity": 0.779893159866333, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/80ad41eba03a33f11140e24a7abe9b72fce1d48d0a6bb104f870bba98afc2e70.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12fed9e295f4a4d1127c1d3c3ebb8fa9129b262a3b12d901cf605e65341d9b0b", "generation_seconds_batch": 13.751605028985068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3310175836086273, "target_z": 0.21289063552393375, "ce": 6.252951145172119, "genuineness": 4.532451152801514, "identity": 0.648108720779419, "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_Pride/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.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": "819bab413fde2cc306fb2cf5bb139fc63d423c7740bb73ced5d8e6cfc20ae95e", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Your message arrived after I had left.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc9a96d260a188aa081458f32e12f0d5985b0bd365392469714b64a7a1182574", "generation_seconds_batch": 16.340430550975725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8824086785316467, "target_z": 1.273437472234728, "ce": 6.38003396987915, "genuineness": 3.7918784618377686, "identity": 0.4438376724720001, "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_Pride/819bab413fde2cc306fb2cf5bb139fc63d423c7740bb73ced5d8e6cfc20ae95e.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "823e5793e0c4dc8ef343c139452006881fe803aae574db2b9792ff1f6c73d7eb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2efd6bf8210870b127ec71819ed1ba5453d4ebe6cc9bbb695450e6bd634708df", "generation_seconds_batch": 19.86886529903859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7686778903007507, "target_z": 1.0546874256607233, "ce": 6.09409761428833, "genuineness": 3.7291181087493896, "identity": 0.3486112952232361, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/823e5793e0c4dc8ef343c139452006881fe803aae574db2b9792ff1f6c73d7eb.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "824b92dd3efc1190a69c294c0038593d9c8f01f0b00ca04abd655a53e48b8da3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f3b5aaf31507dd10f006b732c5232b4f959484b7b22bf0f61847b67fee84dc7", "generation_seconds_batch": 18.517378206946887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9717685580253601, "target_z": 1.4453124596955729, "ce": 6.109982967376709, "genuineness": 3.9425034523010254, "identity": 0.7417522668838501, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/824b92dd3efc1190a69c294c0038593d9c8f01f0b00ca04abd655a53e48b8da3.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": "828245f4d53dfe68c0e77cf3445ce73e4c219a3bab296ee49a6aadeebc7e6452", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8dbbef22b78dd7913478929c5019eeffd633428286d3500e2f6a87e924cda6fd", "generation_seconds_batch": 15.470652983058244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7849251627922058, "target_z": 1.0859374650694964, "ce": 5.9431867599487305, "genuineness": 4.143336772918701, "identity": 0.7323923707008362, "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_Pride/828245f4d53dfe68c0e77cf3445ce73e4c219a3bab296ee49a6aadeebc7e6452.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "82a7d9b916198a8837791a633d6c2dcdff4545b89c0091e2a215d6db5a7d1d6f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e6f07bce336921dcda2745ced9662a7b11f6d97bb6334b76cf2a84ef97d3c27b", "generation_seconds_batch": 23.497758479905315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.511989712715149, "target_z": 2.4843750089565395, "ce": 5.8875885009765625, "genuineness": 3.9299514293670654, "identity": 0.682572603225708, "hypothesis": "De deur 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_Pride/82a7d9b916198a8837791a633d6c2dcdff4545b89c0091e2a215d6db5a7d1d6f.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "82ad929a592eb340baafe4ad151b6faf32cf8672c1afbbdb0aee445443aff235", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4418aecc92f7ddedd4a636b1cec27215ada675ee44ef86d93af2b39a178db8fc", "generation_seconds_batch": 18.56346158706583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1383029222488403, "target_z": 1.7656250197043866, "ce": 5.871703147888184, "genuineness": 3.7542223930358887, "identity": 0.5860128402709961, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/82ad929a592eb340baafe4ad151b6faf32cf8672c1afbbdb0aee445443aff235.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "82c219d50a76ce8480c14d6b3610f138f9d1dae5764c84e5393aec4f4659b0f3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5ea8f20ec88fa60d2ac2b5fcb431f9837907f8934f215da1ca3df5a1384577d6", "generation_seconds_batch": 19.017863897955976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2276628017425537, "target_z": 1.9375000071652315, "ce": 6.149696350097656, "genuineness": 3.8169827461242676, "identity": 0.30580568313598633, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/82c219d50a76ce8480c14d6b3610f138f9d1dae5764c84e5393aec4f4659b0f3.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "82f984fa77ba881e7a14717e38a7872ac1d242f800218173f3e7acf7fbc1b3e0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "29d8617dc6e893eeaf4febc2e34dd9fa33c0487e4c688423ac6b3899d2b0e659", "generation_seconds_batch": 14.68242773693055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6793180704116821, "target_z": 0.8828125528435823, "ce": 6.157639026641846, "genuineness": 4.262581825256348, "identity": 0.7815682888031006, "hypothesis": "La porte ét 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_Pride/82f984fa77ba881e7a14717e38a7872ac1d242f800218173f3e7acf7fbc1b3e0.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "8360d2cf1619cc5e1c5747c0284c6f6ce849e945b39b64daf90455d5931d410b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1cde8eb32bb944e0e287492916c2057370a628efd05b02bf58e1c027f39b19ae", "generation_seconds_batch": 20.033051440957934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9433358907699585, "target_z": 1.3906250053739235, "ce": 6.1020402908325195, "genuineness": 3.8922953605651855, "identity": 0.17537711560726166, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/8360d2cf1619cc5e1c5747c0284c6f6ce849e945b39b64daf90455d5931d410b.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "83aa6b448b0b04b57431d14abeaf10a3c837ddee23e60a380513236ced084cda", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "730c58c2deb6a57bafc76d0c58b66fb183f790320ebdf4cc97bbed9d579312bf", "generation_seconds_batch": 19.595354238990694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8580378293991089, "target_z": 1.226562527765272, "ce": 6.24500846862793, "genuineness": 4.356721878051758, "identity": 0.7326182126998901, "hypothesis": "Ik heb het kleine doosje gevonden. Dat 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_Pride/83aa6b448b0b04b57431d14abeaf10a3c837ddee23e60a380513236ced084cda.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "8422a040c8b14d9a2f20cd7b8113b87adb2c5d1dbecb0d1d9573e8ecf505769b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "018b731de9fb224f85a60577bade73f865ad2bf1bf5ebb147f73d0d4a65da651", "generation_seconds_batch": 21.863680187030695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8296051025390625, "target_z": 1.1718749587999189, "ce": 6.157639026641846, "genuineness": 4.419482707977295, "identity": 0.5534923076629639, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/8422a040c8b14d9a2f20cd7b8113b87adb2c5d1dbecb0d1d9573e8ecf505769b.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": "8427b4c83b9b6b06e6c95e55f5dc8be5ad72b21bd3b0bdb5ca690ce8b1661f6e", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a04670fe9feb95868d3df736e198077edb4ef1bff69480205ff140beef9194f", "generation_seconds_batch": 16.459236596012488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6041744947433472, "target_z": 0.7382812352217101, "ce": 6.173524379730225, "genuineness": 4.3504462242126465, "identity": 0.686274528503418, "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_Pride/8427b4c83b9b6b06e6c95e55f5dc8be5ad72b21bd3b0bdb5ca690ce8b1661f6e.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "84950720ef7ce63b9de4b61a64aa6a9c0697df090f06e38dc1e60ffb6fd9cbe9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "382cce7aeb6e236edd679e32a2fadf1b5ca938c09e568e9fd65635ac7d814142", "generation_seconds_batch": 19.118080600979738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1870447397232056, "target_z": 1.8593751379307064, "ce": 6.173524379730225, "genuineness": 4.231201171875, "identity": 0.6769676804542542, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/84950720ef7ce63b9de4b61a64aa6a9c0697df090f06e38dc1e60ffb6fd9cbe9.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "849e37dc96d694dac9906d6704fdabd907ce4251522c2f3259a791f7f40a4d36", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bd89165f8f7ca3a24d6d71c639f942fbb566e46e0414fcf40ce81bcdacdd73b0", "generation_seconds_batch": 22.16006980894599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7118125557899475, "target_z": 0.9453125170174248, "ce": 6.229123115539551, "genuineness": 4.369274139404297, "identity": 0.6482549905776978, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/849e37dc96d694dac9906d6704fdabd907ce4251522c2f3259a791f7f40a4d36.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "852a44c22cc75b6b3fd961697f06caf766bf9db2ab86833bac7045a4b4df02c9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9398de71b5fd1e7dffdd3acafaf01f14bade425c68a2db5e8d97d939af4a21d8", "generation_seconds_batch": 18.57332594797481, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6346380710601807, "target_z": 0.7968749444694558, "ce": 6.284721851348877, "genuineness": 4.18099308013916, "identity": 0.7388063669204712, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/852a44c22cc75b6b3fd961697f06caf766bf9db2ab86833bac7045a4b4df02c9.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "8578470364cff0e62a6d1f9f0e4a156d371a5fbe2f81fc7b664efcee0642b10d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c49ecf601874e1c9ea84ba80d44a0aafddd1c341c79cb31d6670ed31e2056690", "generation_seconds_batch": 18.58470865606796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3576408624649048, "target_z": 2.1875000931480093, "ce": 6.356205940246582, "genuineness": 4.281409740447998, "identity": 0.6585688591003418, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/8578470364cff0e62a6d1f9f0e4a156d371a5fbe2f81fc7b664efcee0642b10d.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "85ccd81097464bf899e2059227b836ffc6c94f0a80056dc7f0f4814968184516", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "97c4ab1ec4a36d144e36b79c7cf08b93808da09d7192c90193fd33e850505ae0", "generation_seconds_batch": 21.294776351074688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3251463174819946, "target_z": 2.125000014330463, "ce": 5.998785495758057, "genuineness": 3.9173994064331055, "identity": 0.5502495765686035, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/85ccd81097464bf899e2059227b836ffc6c94f0a80056dc7f0f4814968184516.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "865c35ee0d612937a56fa70fe7cd2501cef19f069973a02b3ff606d8d707d166", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0d0dd4a836fef5f307403a51fdb68d0659df54e28e306f750bcee40786c63d5a", "generation_seconds_batch": 19.421157025033608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5696491003036499, "target_z": 0.6718750161217709, "ce": 5.847874641418457, "genuineness": 3.973883628845215, "identity": 0.6078903675079346, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/865c35ee0d612937a56fa70fe7cd2501cef19f069973a02b3ff606d8d707d166.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "86e4d2a007e1cdd8f0af0d6982b93e6dd822380903a6517e0dab9ffe5ac4aa06", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "48d221641abe94cb42fa96cc3464ca2c34bcf3c19acf6fbe5fac7d9372e5fd92", "generation_seconds_batch": 20.780075344024226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6285454034805298, "target_z": 0.7851562943348699, "ce": 6.0305562019348145, "genuineness": 4.306513786315918, "identity": 0.6820574998855591, "hypothesis": "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_Pride/86e4d2a007e1cdd8f0af0d6982b93e6dd822380903a6517e0dab9ffe5ac4aa06.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "87006dbb3e295e9c35c9d9a4e34a3e07638cd1e5f3f06451624009ba511f9619", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f550955538679e867934a4ec8f664b8f8271bbeb7ba991003429438fc873330c", "generation_seconds_batch": 16.9485589240212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9262946844100952, "target_z": 3.2812500967306253, "ce": 6.467403411865234, "genuineness": 4.105680465698242, "identity": 0.4717891812324524, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/87006dbb3e295e9c35c9d9a4e34a3e07638cd1e5f3f06451624009ba511f9619.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "877c1661a10913a96359e7a75dfb494d690a3fac4e59659f0071b740639bb744", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "eb81cbfa743b65daa893f0df444b45ee592380bc26ce418f03b76113abdf42c7", "generation_seconds_batch": 13.736066540004686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7711517810821533, "target_z": 4.906250082400162, "ce": 5.637393951416016, "genuineness": 3.8295347690582275, "identity": 0.5171588659286499, "hypothesis": "La puerta sigue abierta! Te ha dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/877c1661a10913a96359e7a75dfb494d690a3fac4e59659f0071b740639bb744.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": "87977cfa6872b371dbebd3a08c7fb8fde7b60b0bc9a1e46ca2d06a517a734b7a", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The keys are on the kitchen table.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "35d8b0342bfe2c0438efddf46411e298a52025eb5889a7bc31f0be41d67aaf81", "generation_seconds_batch": 16.472860377980396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4559183120727539, "target_z": 0.45312496954776615, "ce": 6.308549880981445, "genuineness": 4.030367851257324, "identity": 0.43487608432769775, "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_Pride/87977cfa6872b371dbebd3a08c7fb8fde7b60b0bc9a1e46ca2d06a517a734b7a.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "87a7fecb71399e4c07d36465d69d25ad2e0e329080c0b7531242eebbf71714c2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3aaa9fd94ba4c7bf136e984d8303aab7b8a633793e63c88a1257cef2015fc683", "generation_seconds_batch": 14.225608340930194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0887670516967773, "target_z": 3.593749802956134, "ce": 6.09409761428833, "genuineness": 4.218649387359619, "identity": 0.19908902049064636, "hypothesis": "Da! Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/87a7fecb71399e4c07d36465d69d25ad2e0e329080c0b7531242eebbf71714c2.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "87b08099b9ac571ac5ee325ebd7cafbc463037f453cff4224906520c6db90a8a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "90981e181a820a13953168ae197055f16d54023adc4aac733c86595cc0c814c9", "generation_seconds_batch": 19.339755540015176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.462453842163086, "target_z": 4.312499792208286, "ce": 6.324435234069824, "genuineness": 3.9048471450805664, "identity": 0.6396183967590332, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/87b08099b9ac571ac5ee325ebd7cafbc463037f453cff4224906520c6db90a8a.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "87c3da07ecc7119d3621345ef5f1d0df9e0a7c22483be9ffde024e07b42d4f5c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "137d44550f02921c1cf3f3de0fa2bfe6ad910fba9711e11e973c6253a23541d7", "generation_seconds_batch": 19.053912485018373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5777727365493774, "target_z": 0.6875000358261575, "ce": 6.157639026641846, "genuineness": 4.482243061065674, "identity": 0.662274956703186, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/87c3da07ecc7119d3621345ef5f1d0df9e0a7c22483be9ffde024e07b42d4f5c.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "882e949e5cfa5265c1e52f14d54e50d332f05e39b417333e2cb03ae395b6d0a0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "90be85e55fecb8f0aec3ce32d4ea5e577ed20f58c576fc9f31ef6c67a7020d71", "generation_seconds_batch": 22.257037751958705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8052342534065247, "target_z": 1.125000014330463, "ce": 6.133810997009277, "genuineness": 4.068024158477783, "identity": 0.5013065934181213, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/882e949e5cfa5265c1e52f14d54e50d332f05e39b417333e2cb03ae395b6d0a0.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "8840ee35a669ea4f841f5114f5b1a468779c9eee16102d0b482651a716e6c249", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "045e0a366f668f4f6372bc94d7653a904fe5aa80251c79511932237ae092c9c7", "generation_seconds_batch": 20.59188482898753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6793180704116821, "target_z": 0.8828125528435823, "ce": 6.173524379730225, "genuineness": 4.15588903427124, "identity": 0.7592630386352539, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/8840ee35a669ea4f841f5114f5b1a468779c9eee16102d0b482651a716e6c249.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "8888936b073f017efe08642e01496e73de5908cd697706ad6d0e900fbc23c4c4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ba5e01bc81752eb6373162ae07e51490bdf2d775cf826331827dfe1ccd0c5340", "generation_seconds_batch": 14.168399067013524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9839540123939514, "target_z": 1.4687499892521527, "ce": 6.221180438995361, "genuineness": 4.093128204345703, "identity": 0.6182054281234741, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/8888936b073f017efe08642e01496e73de5908cd697706ad6d0e900fbc23c4c4.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": "889011c3c93325a0c13cbf929876acf5cd37491b6cd22a8f3770f1c63fc33b11", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a30b95a7baa0d531d58c013dfd07731d2d98e1d7f7ceee329b64350ae9ea756", "generation_seconds_batch": 19.34367679199204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5615254640579224, "target_z": 0.6562499964173842, "ce": 6.086154937744141, "genuineness": 3.9048471450805664, "identity": 0.6062067747116089, "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_Pride/889011c3c93325a0c13cbf929876acf5cd37491b6cd22a8f3770f1c63fc33b11.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": "88a61ea0b7d6121616d67aa863a4434ffc65b432d9679832dfc97d41ffe6bc6c", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be821617e61bdc52ded69482c9cacd56d73525dfd53a09808fcf720b30c58a40", "generation_seconds_batch": 16.26609912898857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6001126766204834, "target_z": 0.7304687253695167, "ce": 6.173524379730225, "genuineness": 4.143336772918701, "identity": 0.6732620000839233, "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_Pride/88a61ea0b7d6121616d67aa863a4434ffc65b432d9679832dfc97d41ffe6bc6c.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "88f3d3e81f6d5004439378e1396df1d6ce7197bede4b38e371ca4eac6fda8d5d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7e9af43b8a9a302bf9f2b4f73bbfabc33d50157c9764097f0630e21fb8fb1950", "generation_seconds_batch": 19.626927951001562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8052342534065247, "target_z": 1.125000014330463, "ce": 6.141753673553467, "genuineness": 4.068024158477783, "identity": 0.8154860734939575, "hypothesis": "De deur staan 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_Pride/88f3d3e81f6d5004439378e1396df1d6ce7197bede4b38e371ca4eac6fda8d5d.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": "896f06f91abab96c80c63099dd154a467e086899f01bc778519d90c2c7173b46", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I wrote the number on the envelope.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "63b2d1e8812cdda0fcb303a1e3b527b5394331f6e478260c84aa9b0e134c527b", "generation_seconds_batch": 20.26234541798476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5436902046203613, "target_z": 4.468749989252153, "ce": 6.419747352600098, "genuineness": 3.961331605911255, "identity": 0.31015321612358093, "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_Pride/896f06f91abab96c80c63099dd154a467e086899f01bc778519d90c2c7173b46.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "8975682ad08e0a6aff05e0bb3c9146f3f68d2af74b3a215f945d3b085696f2d0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9fef6c327f4ed0fe987e8f972c548e4e0663f40da028a9beb87eb825b44a1fa7", "generation_seconds_batch": 20.600227201008238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6386998891830444, "target_z": 0.8046874543216492, "ce": 6.348263263702393, "genuineness": 4.356721878051758, "identity": 0.5387107729911804, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/8975682ad08e0a6aff05e0bb3c9146f3f68d2af74b3a215f945d3b085696f2d0.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": "89a505cd0c029e5be70beab06fdb62f04af582baa51b7c9a4db84b6ddfb0991d", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3004237b100df7f1edcd5e9cc4e2fa19e1e8c9ca306cd4b57732d2854217fca", "generation_seconds_batch": 14.840154016041197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.585896372795105, "target_z": 0.7031250555305442, "ce": 6.141753673553467, "genuineness": 3.7667744159698486, "identity": 0.6708123683929443, "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_Pride/89a505cd0c029e5be70beab06fdb62f04af582baa51b7c9a4db84b6ddfb0991d.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "8a0a866cdf89647ee4bdf1545736232fac85fb230fe7e2bdf3579f647aa27a8b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f71e9119ce6d6f3b4f6c6e67c53f5db4ae3b41a488ffc515edf71b730aca2018", "generation_seconds_batch": 16.522134819999337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.663070797920227, "target_z": 0.851562513434809, "ce": 6.292664527893066, "genuineness": 4.168440818786621, "identity": 0.5531562566757202, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/8a0a866cdf89647ee4bdf1545736232fac85fb230fe7e2bdf3579f647aa27a8b.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": "8a7f7dff2efeaf8a83ebb7a1be5e4df6eab01baea3a45149374f038d3f645235", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "38fdd1718f6c265cf01051d5235ee88892af5fec96bac61aefb0143922eda0ac", "generation_seconds_batch": 13.746408510953188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41022294759750366, "target_z": 0.36523440567614734, "ce": 6.332377910614014, "genuineness": 4.193545341491699, "identity": 0.5116466283798218, "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_Pride/8a7f7dff2efeaf8a83ebb7a1be5e4df6eab01baea3a45149374f038d3f645235.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": "8b15425710e69a049ae96bf109257d1ff590e31187e78e29e365f60ea94264a8", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "689769b6f5dd12059d4bcd88cf93986f9b052112c5804c55f3a43ca3b51f9285", "generation_seconds_batch": 18.623446869081818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4417019784450531, "target_z": 0.42578124238694154, "ce": 6.213237762451172, "genuineness": 3.961331605911255, "identity": 0.6011837720870972, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vaya.", "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_Pride/8b15425710e69a049ae96bf109257d1ff590e31187e78e29e365f60ea94264a8.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": "8b33c618babb6099dbfe6e2e5f1ef8f01458e86631daae8dccebd6a49bb578b7", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Escribí el número en el sobre.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ff4b1234059cb9ffb232cedb470aad942a10556309baf7ad314e8194f9305a47", "generation_seconds_batch": 16.571573019959033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.739451289176941, "target_z": 2.921875102104549, "ce": 6.229123115539551, "genuineness": 4.293961524963379, "identity": 0.66725093126297, "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_Pride/8b33c618babb6099dbfe6e2e5f1ef8f01458e86631daae8dccebd6a49bb578b7.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "8c2be90f37fe9c9771b21bb5aebbd9d865d3b6605b10bca1b65f2ef383dd5b4a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9b956ee16929ee9801add56eb765fa06a99c46ced5d42565f7674950eecb8b73", "generation_seconds_batch": 14.85209869092796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5249691605567932, "target_z": 0.5859375223913484, "ce": 6.300607204437256, "genuineness": 4.394378662109375, "identity": 0.4489748477935791, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/8c2be90f37fe9c9771b21bb5aebbd9d865d3b6605b10bca1b65f2ef383dd5b4a.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "8d1dbd20f5dbeab62501ad6b357d144897b0fa162a037dcfaf9415061c3c213d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0cf17295fe7b9bfba6ddd2e3837409392fd592e3991ab60f37dd7531dca8911a", "generation_seconds_batch": 19.118351590936072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8369348049163818, "target_z": 3.1093751092697803, "ce": 6.205295085906982, "genuineness": 4.362998008728027, "identity": 0.43354707956314087, "hypothesis": "Die Tür 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_Pride/8d1dbd20f5dbeab62501ad6b357d144897b0fa162a037dcfaf9415061c3c213d.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "8d9920dfbc2ccafb5b9e82fd9959a660286b46f4cb5f2632b8b6dc0134ae3bc8", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "516db24633db861067828f871e5562c65a479025a716c4ebbe011beb20838e7d", "generation_seconds_batch": 20.360231151920743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5005982518196106, "target_z": 0.5390624632781885, "ce": 6.252951145172119, "genuineness": 4.20609712600708, "identity": 0.48906272649765015, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/8d9920dfbc2ccafb5b9e82fd9959a660286b46f4cb5f2632b8b6dc0134ae3bc8.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": "8db763b4bb7e393be6448f9747863e10967f55e0afc821f2284aa7caca60591c", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc0c9d4c9ae6bccf03c5abd47eb0635a065ef4e313e6c1871e318712eac433f8", "generation_seconds_batch": 18.623446869081818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7402452230453491, "target_z": 0.999999971339074, "ce": 6.165581703186035, "genuineness": 3.9801597595214844, "identity": 0.6118128299713135, "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_Pride/8db763b4bb7e393be6448f9747863e10967f55e0afc821f2284aa7caca60591c.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "8e097fcd4e4a63746cae3376267e0ba0564948bc8605397ddc67d87651f72355", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a697a0a3b98ecf59c23697015fc5400b2007ec7d75ba71b17b4aa929d5f506e1", "generation_seconds_batch": 14.68242773693055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5940199494361877, "target_z": 0.7187499605912268, "ce": 6.1020402908325195, "genuineness": 4.111956596374512, "identity": 0.6094774007797241, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/8e097fcd4e4a63746cae3376267e0ba0564948bc8605397ddc67d87651f72355.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "8ebdd0874fa8c9fe8ef7b5a8aa62ffeb768e5aa72877f755c4265b92d6bd56d5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f8aebe273100c60ff0a96dfadab08a7602fa40b6e9e0dc8b8d101761239c50f7", "generation_seconds_batch": 20.74951523495838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8092960715293884, "target_z": 1.1328125241826563, "ce": 5.998785495758057, "genuineness": 3.9048471450805664, "identity": 0.5599254965782166, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/8ebdd0874fa8c9fe8ef7b5a8aa62ffeb768e5aa72877f755c4265b92d6bd56d5.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "8ff9dffbc55675e9baf610e12a16acb6fe410a6880652d8349aca49b0de82fa7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7734c26fb14afa5379aad52b93d4032caed677dff0dae5cc91d39e86c249fe0c", "generation_seconds_batch": 18.621807985007763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5688551664352417, "target_z": 2.593750146887246, "ce": 6.340320587158203, "genuineness": 4.281409740447998, "identity": 0.4876627027988434, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/8ff9dffbc55675e9baf610e12a16acb6fe410a6880652d8349aca49b0de82fa7.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "901467fc076579c958a482e812111d5326eaf54c68ff8964ba28b26c31d0d1f5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bfcbd9724f7479cc8b81e63465a013371f9475979bad544f561ceb03168749d2", "generation_seconds_batch": 21.866524509969167, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6411736011505127, "target_z": 4.656249767129976, "ce": 6.1894097328186035, "genuineness": 3.9299514293670654, "identity": 0.2840355336666107, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/901467fc076579c958a482e812111d5326eaf54c68ff8964ba28b26c31d0d1f5.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": "9029442c4085a2b126b0a2cd25f6e8550c28e70ba0673ecd968270fa0eafe7a9", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "216bee63849ea22f38d563d14252c7c2d0f6137c3c42fdb94ec5493b63e6e43f", "generation_seconds_batch": 16.512293178937398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9344183206558228, "target_z": 3.296875116435012, "ce": 6.268836498260498, "genuineness": 3.6914620399475098, "identity": 0.3430204391479492, "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_Pride/9029442c4085a2b126b0a2cd25f6e8550c28e70ba0673ecd968270fa0eafe7a9.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "9057e513ff67aa0ccae033e7ba456bcb883a706548afea7fed53e9c97543c658", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f7d801b26beaf44fdd411c151bdcc07f7735dbb18b2ecfca7302ae3f35d3ea89", "generation_seconds_batch": 19.565635862061754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.292651891708374, "target_z": 2.0625001648003245, "ce": 6.181467056274414, "genuineness": 3.8169827461242676, "identity": 0.1636546105146408, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9057e513ff67aa0ccae033e7ba456bcb883a706548afea7fed53e9c97543c658.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "907d60e52425939f60de003ccf22fb404e3563a4f8f821202fbf19c73f0fb99a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b2c260f8971e16991590bbd252cc875721749127984093c8e177e6466a064b71", "generation_seconds_batch": 19.71918007801287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49247461557388306, "target_z": 0.523437443573802, "ce": 6.252951145172119, "genuineness": 4.243753433227539, "identity": 0.7158137559890747, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/907d60e52425939f60de003ccf22fb404e3563a4f8f821202fbf19c73f0fb99a.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": "90a0a493161403fcc8c3a4502a26469d53308d7e6a40d195d095117420927a6e", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7f1e6eec7c1a35802096d4b6696612a4e23cc8f7c121d0d3d1acc1263de358a", "generation_seconds_batch": 19.367547966889106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.081437587738037, "target_z": 1.6562501110610883, "ce": 6.23706579208374, "genuineness": 4.250029563903809, "identity": 0.7610673904418945, "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_Pride/90a0a493161403fcc8c3a4502a26469d53308d7e6a40d195d095117420927a6e.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "912f27cbc298548ac741fd13d6ade3656ac026d0a5f174b345d03bff30d8145d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "75fc944a21d8b5ddd4e3952aa7ba0b830ba67be30ce694ba806c2983023de305", "generation_seconds_batch": 19.61363655596506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7158743739128113, "target_z": 0.9531250268696181, "ce": 6.125868320465088, "genuineness": 4.093128204345703, "identity": 0.5483889579772949, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/912f27cbc298548ac741fd13d6ade3656ac026d0a5f174b345d03bff30d8145d.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "9147ec1eececa47fd668116d26b95e8077b34d2e4e528266d5b408649e67debb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "093ec5f1837249fce505d45779d47913488b131737774899563ff80d21c70656", "generation_seconds_batch": 14.905183324939571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8011724352836609, "target_z": 1.1171875044782698, "ce": 6.24500846862793, "genuineness": 3.9801597595214844, "identity": 0.34590446949005127, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9147ec1eececa47fd668116d26b95e8077b34d2e4e528266d5b408649e67debb.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "9202ba21af6eac79e5e5a63a5e71640c710158991f4beca615f861550b9d7585", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "82d6d58c958dd1cfeef9855c9e36af5236c83bb9e1558183414b005b2dcbd37e", "generation_seconds_batch": 22.03461676905863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6996271014213562, "target_z": 0.9218749874608448, "ce": 6.205295085906982, "genuineness": 4.042920112609863, "identity": 0.5612421035766602, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9202ba21af6eac79e5e5a63a5e71640c710158991f4beca615f861550b9d7585.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": "928d819461583c15ed6c98608aacc23b9edcaad70c868d6151077ba9314690cb", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The road turns left behind the bridge.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ca058c92ab9351bd83d8a9ce39d313db54aa196dcf10445060660f9a30e9d82", "generation_seconds_batch": 14.541702192043886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5757418274879456, "target_z": 0.6835937809000608, "ce": 6.372091293334961, "genuineness": 3.860914945602417, "identity": 0.366789847612381, "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_Pride/928d819461583c15ed6c98608aacc23b9edcaad70c868d6151077ba9314690cb.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "929b0aa868b9c34e59fb7a15483209ab8d562762ee9d1abc9dc5b7e7b3efc56e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d81780f49671ccb55e0bb148e58303478026b7da12d5f954a7e17710b060d446", "generation_seconds_batch": 19.260617975960486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.202497959136963, "target_z": 3.8125000788175467, "ce": 6.372091293334961, "genuineness": 3.936227321624756, "identity": 0.5458098649978638, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/929b0aa868b9c34e59fb7a15483209ab8d562762ee9d1abc9dc5b7e7b3efc56e.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "9355e0109483a8312a821c3b38ec107a5e4d6f677fd8f739cfbeca8a9d100c11", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "938321060216725354cf4be4c49d882df8e9ff0905955afb99f4a2da19e048c1", "generation_seconds_batch": 18.964482816983946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6001126766204834, "target_z": 0.7304687253695167, "ce": 6.1020402908325195, "genuineness": 4.362998008728027, "identity": 0.6158596277236938, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la 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_Pride/9355e0109483a8312a821c3b38ec107a5e4d6f677fd8f739cfbeca8a9d100c11.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": "93dc3b7a55a7f212965e277c25dc235f2cfc407610dffd498a3111adfacac304", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba7ae4d508db08e95acc5295fe045f8c9d54ae4625b1b3d830a5b2f515785671", "generation_seconds_batch": 23.074030383024365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3452339172363281, "target_z": 0.24023436268475837, "ce": 6.054384231567383, "genuineness": 4.030367851257324, "identity": 0.7556179761886597, "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_Pride/93dc3b7a55a7f212965e277c25dc235f2cfc407610dffd498a3111adfacac304.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "94ce86b4ec2d9f9dd60039366134a3f466ec2668ce20eece2fb19620daae0c19", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8664d662d8535044ae77d447876c1f5adb12e2d8cbe296adc362633a01ea4c82", "generation_seconds_batch": 18.616662285057828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3413935899734497, "target_z": 2.156250053739236, "ce": 6.0305562019348145, "genuineness": 3.8797430992126465, "identity": 0.38957688212394714, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/94ce86b4ec2d9f9dd60039366134a3f466ec2668ce20eece2fb19620daae0c19.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "954e08c62307c9893f19a77b4bf17956f397fd5723a9d77bc7cca87a51bd9a80", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8c2d13eee3f58df77068a9731af68100dc5e1d2c320fc90258b7ba1cbb147428", "generation_seconds_batch": 23.667363267042674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0976847410202026, "target_z": 1.6874999211824535, "ce": 6.213237762451172, "genuineness": 4.2249250411987305, "identity": 0.41891002655029297, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/954e08c62307c9893f19a77b4bf17956f397fd5723a9d77bc7cca87a51bd9a80.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "95c51b919ebc52a021735c7850f59bd8cc27c2001d9dc63a53cf10cc975b7e3b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8a4c635bf61302830c3750ba4750230ed911dc6161249c7401b80bd85ba52c19", "generation_seconds_batch": 19.73627337499056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.472165584564209, "target_z": 0.4843750089565394, "ce": 6.086154937744141, "genuineness": 4.394378662109375, "identity": 0.6556993722915649, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/95c51b919ebc52a021735c7850f59bd8cc27c2001d9dc63a53cf10cc975b7e3b.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "96090af8745e0383a76d4ac5cc917ffea6a07f620b75bb7eb2b5534f52596d3d", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2097976b4045e0f8e4b3d514297f565ab15666de6f9a3acb15b89bc00f0d2425", "generation_seconds_batch": 17.142621400998905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8133578300476074, "target_z": 1.1406249193911457, "ce": 6.09409761428833, "genuineness": 3.9550557136535645, "identity": 0.6058083176612854, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/96090af8745e0383a76d4ac5cc917ffea6a07f620b75bb7eb2b5534f52596d3d.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "9726df98c01a0d8e4850c79d75d24b9739a33ef479edab91c0e9a57ecf6096e9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d1ad452c7435fcecd69f41bdadb6e5ac0fe37234cbe7273bfec5c8087d6360e0", "generation_seconds_batch": 20.563671389012598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1504883766174316, "target_z": 1.7890625492609666, "ce": 6.268836498260498, "genuineness": 3.798154592514038, "identity": 0.1472199410200119, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9726df98c01a0d8e4850c79d75d24b9739a33ef479edab91c0e9a57ecf6096e9.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "977ed507d2e8bce1b8670cd55764f73181c61d8168ee768f004bf782e620e065", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b2aa66ce05b95fb0f75fe981af3e244ae9fc22c69eb75915d15d66b5a856cb9a", "generation_seconds_batch": 18.42805007402785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9880158305168152, "target_z": 1.476562499104346, "ce": 6.1020402908325195, "genuineness": 4.293961524963379, "identity": 0.6447312831878662, "hypothesis": "J'ai trouvé la 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_Pride/977ed507d2e8bce1b8670cd55764f73181c61d8168ee768f004bf782e620e065.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": "97d2f41ec778761f9c792ba909fec48482411c67a65eb9aa56bcf99ccef21b36", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "be246de6cdcd65d98cf4b7d44307c53e7304fb06cb560d4aa7c849329b5767e4", "generation_seconds_batch": 15.470652983058244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3007755279541016, "target_z": 2.078125184504711, "ce": 6.062326908111572, "genuineness": 4.118232727050781, "identity": 0.5000526309013367, "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_Pride/97d2f41ec778761f9c792ba909fec48482411c67a65eb9aa56bcf99ccef21b36.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "98239372ac000df570b304ab75610e7442c3b4a60d18bbe7a2592bfee729e422", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f131a0e4e4fb0149586d54a1fa110875b0f5647f30f4009b77f031895d17be13", "generation_seconds_batch": 17.331555669079535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5594945549964905, "target_z": 0.6523437414912876, "ce": 6.046441555023193, "genuineness": 4.118232727050781, "identity": 0.4931687116622925, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/98239372ac000df570b304ab75610e7442c3b4a60d18bbe7a2592bfee729e422.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": "98862ab53dc42df6f6ed948caf54cbbb8b372436bd285b651f9282920db9ebce", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "246a76d71b85a46f5ddd277848915c022628772cc74101aed74e3936379c9a0f", "generation_seconds_batch": 13.811579633969814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.955521285533905, "target_z": 1.4140624202867995, "ce": 6.133810997009277, "genuineness": 4.074300289154053, "identity": 0.48614242672920227, "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_Pride/98862ab53dc42df6f6ed948caf54cbbb8b372436bd285b651f9282920db9ebce.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "995b07cff59c8c66684147756a14735c885aeb4e0ecb3466bc9efa5fafa2c1a6", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "13e7d5d88e1a06e2b7efbfa63e69df45c76aa4d6f65e8577ed9605f635f7f13a", "generation_seconds_batch": 19.440815508016385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7483688592910767, "target_z": 1.0156249910434607, "ce": 6.173524379730225, "genuineness": 4.293961524963379, "identity": 0.6444780826568604, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/995b07cff59c8c66684147756a14735c885aeb4e0ecb3466bc9efa5fafa2c1a6.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": "99a4235588426d45a6dbd89557b190623f7f55531bdfa046c4c507b0a4b14999", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "528abc4150001c412ff6c78d51583765a8915930a6d6af1926800bb8cffa9428", "generation_seconds_batch": 15.382408762932755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8125638961791992, "target_z": 3.0625000501566206, "ce": 6.221180438995361, "genuineness": 4.1998209953308105, "identity": 0.6226793527603149, "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_Pride/99a4235588426d45a6dbd89557b190623f7f55531bdfa046c4c507b0a4b14999.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "e94b9df2039f9628866bbc25c9aff923712fc1a73cacfd295c4a3c2e0ce71994", "generation_seconds_batch": 16.289771214011125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5249691605567932, "target_z": 0.5859375223913484, "ce": 6.38797664642334, "genuineness": 4.68307638168335, "identity": 0.5895496606826782, "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_Pride/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "99e1700f273adc540e1b887307774341d3931c00d7f22fce87a186831fa39100", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a8ebd14cd3f427779bc85944cb981a4ed5e951e2b83c187f4f13824c2a314e6", "generation_seconds_batch": 22.105004520970397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0448812246322632, "target_z": 1.5859375223913483, "ce": 6.197352409362793, "genuineness": 4.080576419830322, "identity": 0.6401256322860718, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/99e1700f273adc540e1b887307774341d3931c00d7f22fce87a186831fa39100.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "9aaae044ee803473be59cd8b23b6267614d7daa6b97a523dcff6b576e60f04a2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "57809838f531e885f30e3f90f91e87b1c078187f58afc5bb87bb88996edd9479", "generation_seconds_batch": 18.52793327101972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6988331079483032, "target_z": 2.8437500035826155, "ce": 6.205295085906982, "genuineness": 4.074300289154053, "identity": 0.3325103521347046, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9aaae044ee803473be59cd8b23b6267614d7daa6b97a523dcff6b576e60f04a2.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "9b66ef38ca906c0880ce66455c5e4b2fef840c957b766e52d33e74a004d463dc", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b53ff99603054867729eb188a980b9bde454089b6d3c33de8a970ddb720d6a77", "generation_seconds_batch": 19.04155124805402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.430753469467163, "target_z": 2.328125041200081, "ce": 6.332377910614014, "genuineness": 4.300237655639648, "identity": 0.22791148722171783, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9b66ef38ca906c0880ce66455c5e4b2fef840c957b766e52d33e74a004d463dc.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "9bbc6f7e099b5e326ce30077466692150fa18765017a3b158286bf113bfe1940", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4378f6d3959ecb6efe65acd3b1cd1d6de380b7c58bb9a92661fb88fe5021da5d", "generation_seconds_batch": 18.70184497802984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4957425594329834, "target_z": 2.453125198835174, "ce": 5.8875885009765625, "genuineness": 4.017816066741943, "identity": 0.5971910953521729, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9bbc6f7e099b5e326ce30077466692150fa18765017a3b158286bf113bfe1940.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": "9bc8e13caf6c81c07ecf6f460a35f4f5314e82bb7cb6ea24318d31ad2ced9a64", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Escribí el número en el sobre.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4a058942839c34e1ddd15177203706ae81c9f70b946e6a8ac6f758d67097b4a4", "generation_seconds_batch": 16.571573019959033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1464265584945679, "target_z": 1.7812500394087734, "ce": 5.903473377227783, "genuineness": 3.9550557136535645, "identity": 0.3612179160118103, "hypothesis": "Es decir Radiburé le jalo sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.2631578947368421, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9bc8e13caf6c81c07ecf6f460a35f4f5314e82bb7cb6ea24318d31ad2ced9a64.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "9bf4869ecd50a5c508de69948181241da9fb16ae19c65b77e9eba44edeedc19a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "28b1521e8f5bf40886f19e3685a2e47ba4e01f21c7b380bfea688f9ec155bf4b", "generation_seconds_batch": 14.905183324939571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9067795276641846, "target_z": 1.3203124167041838, "ce": 6.1894097328186035, "genuineness": 3.9676074981689453, "identity": 0.27052584290504456, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9bf4869ecd50a5c508de69948181241da9fb16ae19c65b77e9eba44edeedc19a.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "bfcca3f03a75a4e5fa30a514681c1f17fa9a3b4be959942e94b148156342ea9a", "generation_seconds_batch": 16.683026059996337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48841285705566406, "target_z": 0.5156250483653126, "ce": 6.300607204437256, "genuineness": 4.1998209953308105, "identity": 0.4744766354560852, "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_Pride/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "9c3440a934929cbecd784d704e3b06f72bdd66142b8e189c636ffca7a84c6103", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "125d0aab43a14f6e14573e2910f9bc7b4da51f9ad7c2d64c68d7b203b1d47fc9", "generation_seconds_batch": 18.83372278395109, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.494948387145996, "target_z": 4.374999871025833, "ce": 6.284721851348877, "genuineness": 3.9425034523010254, "identity": 0.3932569622993469, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9c3440a934929cbecd784d704e3b06f72bdd66142b8e189c636ffca7a84c6103.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "9c47136e7806a86f75083542646d991177b746d6922410e3a86634591ebdddad", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9f4da1618ad2b80a2936f73e3c987f2edae60286da2c249dd2981c30eb25dae6", "generation_seconds_batch": 18.429389627999626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3332699537277222, "target_z": 2.1406250340348496, "ce": 6.181467056274414, "genuineness": 4.005263805389404, "identity": 0.5702309608459473, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9c47136e7806a86f75083542646d991177b746d6922410e3a86634591ebdddad.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "66853535120a8332cddf24dc8ad8783861dd7d6fd83d2693367849da73ac1000", "generation_seconds_batch": 13.691055019036867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38788294792175293, "target_z": 0.3222656014890841, "ce": 6.221180438995361, "genuineness": 4.231201171875, "identity": 0.652835488319397, "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_Pride/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "9cbcbfd69e57f172672598f8bcb53a5db9030f97d1645b3abe78844ce6842079", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "95da798e0a33d1e2098cfef4b8d5367eb22176226caa4060131d04d6183810e9", "generation_seconds_batch": 19.941161594935693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3665584325790405, "target_z": 0.28124998208692126, "ce": 6.41180419921875, "genuineness": 4.532451152801514, "identity": 0.34531110525131226, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9cbcbfd69e57f172672598f8bcb53a5db9030f97d1645b3abe78844ce6842079.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "9cbda69428a2f51f6f84c51e400d8e17e0dee24e783dfbe097b527ea911c47b9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "66877e00320e1988f7db618f132f8ff33a937669656b76471598f30537360c23", "generation_seconds_batch": 21.180813926970586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44271743297576904, "target_z": 0.42773436984998986, "ce": 6.038498878479004, "genuineness": 4.15588903427124, "identity": 0.700743556022644, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9cbda69428a2f51f6f84c51e400d8e17e0dee24e783dfbe097b527ea911c47b9.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "9cfcaad194003f7475a6cf55fe10af291f4d136d174a075f32c0de532ad5600a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6a72d3e68077e72e152b78ad29dd6d37cfcc27ab0aaef10ef574f202ca09c1d9", "generation_seconds_batch": 18.436440752004273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7077507376670837, "target_z": 0.9375000071652315, "ce": 6.348263263702393, "genuineness": 4.099404335021973, "identity": 0.4970547556877136, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9cfcaad194003f7475a6cf55fe10af291f4d136d174a075f32c0de532ad5600a.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "9d77cc2a99abebedac548d69f01d511184ce55ea5924a98371a40a9d09c88287", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d9100a02b39d0133e0d7a3e0970872e759d780ca73d6c564dbc341753956af08", "generation_seconds_batch": 13.916918847011402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5716800093650818, "target_z": 0.6757812710478676, "ce": 6.1020402908325195, "genuineness": 4.406930446624756, "identity": 0.49044740200042725, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "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_Pride/9d77cc2a99abebedac548d69f01d511184ce55ea5924a98371a40a9d09c88287.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "9d93c9d15d2d9018cf2075b37736dffd28213f75f607e337aed8ccbb5d218c2a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "25b7bbf77b7b16e98b31441a7c175fc3befc6a323db41c7388d6711ff3f34e72", "generation_seconds_batch": 19.103126816102304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1545501947402954, "target_z": 1.79687505911316, "ce": 5.732706069946289, "genuineness": 4.042920112609863, "identity": 0.5302626490592957, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9d93c9d15d2d9018cf2075b37736dffd28213f75f607e337aed8ccbb5d218c2a.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "9e362fae263824bf9c216156520d53bf1be7e24cbd072e1cb0c5d951d675a632", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0ae8ddf986cc6e73257b9a5b940ecc4be8ff68e3b0971de5746f21648d76bc25", "generation_seconds_batch": 19.551696677925065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5737109184265137, "target_z": 0.6796875259739642, "ce": 6.372091293334961, "genuineness": 4.532451152801514, "identity": 0.3009706735610962, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9e362fae263824bf9c216156520d53bf1be7e24cbd072e1cb0c5d951d675a632.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "9ea496c7c2d4e6531038891c7b5d1871734d33a552b66e46531f027c28441ab4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c318706b30f645bf8ade6a40e72a5ce95ab013c00fffcabda49a02f1ab11b697", "generation_seconds_batch": 18.577518453937955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7686778903007507, "target_z": 1.0546874256607233, "ce": 6.165581703186035, "genuineness": 4.030367851257324, "identity": 0.6505146026611328, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9ea496c7c2d4e6531038891c7b5d1871734d33a552b66e46531f027c28441ab4.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "9f9e031ca75bf9c9b3554da16888dd4b41e2496c7654c72e8a16161ff7e4b78f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d388020a230ff3997981e13b038ac4a59e58cbec91669a1011b3458a0fc1dedc", "generation_seconds_batch": 17.021484562079422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0164484977722168, "target_z": 1.5312499534259953, "ce": 6.022613525390625, "genuineness": 3.9425034523010254, "identity": 0.6330172419548035, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9f9e031ca75bf9c9b3554da16888dd4b41e2496c7654c72e8a16161ff7e4b78f.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "9fb0d493309d4fc9783f4da4b84119dedab91656b66c1f00a1eaac5d6579a9d2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "72c4b279ed1cb745982cbf9b6b31385af1dfb5f91751ba6d1ff08228e3284aa1", "generation_seconds_batch": 19.663066647946835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5980817675590515, "target_z": 0.72656247044342, "ce": 6.006728172302246, "genuineness": 4.18099308013916, "identity": 0.18268144130706787, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9fb0d493309d4fc9783f4da4b84119dedab91656b66c1f00a1eaac5d6579a9d2.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "9fce41dc92a8ba276a83ef907f53a9942863c2f03ba6043395ca05cc4ff16c6c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c554188a57d10ef15837b0d6a63fab970e3e8832592584b814f571b3213fb0e6", "generation_seconds_batch": 14.948380362940952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3487231731414795, "target_z": 4.09374997492169, "ce": 6.348263263702393, "genuineness": 4.086852550506592, "identity": 0.4843105375766754, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/9fce41dc92a8ba276a83ef907f53a9942863c2f03ba6043395ca05cc4ff16c6c.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": "a00cdce94fa4d71671c502de8b6651944da1fae2f8d6f6b93ae33eeec0e4f5c3", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3897ef0707a0cdd31b6b1766bcd0e04f046c48ec2524edc9f6b5c62bad2f95e", "generation_seconds_batch": 14.843053326942027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26298221945762634, "target_z": 0.08203126746525179, "ce": 6.078212261199951, "genuineness": 4.174716949462891, "identity": 0.7135691046714783, "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_Pride/a00cdce94fa4d71671c502de8b6651944da1fae2f8d6f6b93ae33eeec0e4f5c3.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "a04200bad4b459f1fe2a48a00055fbf7c8b8ff8777a64677e8bdbc15b49c43d3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "479427a9869990dbb3cea5a05670883c48d399f32824ef301a1ab62a6fdd901d", "generation_seconds_batch": 18.79686761298217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6086790561676025, "target_z": 4.59374968831243, "ce": 6.125868320465088, "genuineness": 3.823258876800537, "identity": 0.36479008197784424, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a04200bad4b459f1fe2a48a00055fbf7c8b8ff8777a64677e8bdbc15b49c43d3.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "a0da1906786ec0435dcc644106b832dd17320a3dac6bb556625a2c103fb23755", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "44de4f8608f410436bdf3f70fed73fa0930b3516c23930e247bfd9c95ae8d096", "generation_seconds_batch": 13.729134320979938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0164484977722168, "target_z": 1.5312499534259953, "ce": 6.300607204437256, "genuineness": 4.168440818786621, "identity": 0.29996004700660706, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a0da1906786ec0435dcc644106b832dd17320a3dac6bb556625a2c103fb23755.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": "a1f7838dc35e24595cdf202ecb503bc56bdfb15dd09e5b9a18b89640a1f6e2fc", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The keys are on the kitchen table.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3018cdb33a7303a0ba219ad90b3c6e7dc7792ed2990893d80a0a876546e50c6a", "generation_seconds_batch": 18.54634471994359, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5209073424339294, "target_z": 0.5781250125391552, "ce": 6.268836498260498, "genuineness": 3.998987913131714, "identity": 0.30994611978530884, "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_Pride/a1f7838dc35e24595cdf202ecb503bc56bdfb15dd09e5b9a18b89640a1f6e2fc.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "a31f338efc36e8614e32463d9eb4b1a358c3357f09c3c5e70f8ff7889c831384", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83da9730059800cf375393f4ebf51f9c0ad12c6ef02f0121aa5a993585a03d50", "generation_seconds_batch": 19.367440005065873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.443732887506485, "target_z": 0.4296874973130382, "ce": 6.260893821716309, "genuineness": 4.545003414154053, "identity": 0.564572274684906, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a31f338efc36e8614e32463d9eb4b1a358c3357f09c3c5e70f8ff7889c831384.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "a32f421b960f19d6df984793025b74cfba9839b1dfdc9f5fcd5a62076b2a280b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f93a4c4625c5c5a22c56bb17a573a6b5b7d9dbaea4bea9f0a0f27f7ddcb113fa", "generation_seconds_batch": 19.367440005065873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5201133489608765, "target_z": 2.500000028660926, "ce": 6.1894097328186035, "genuineness": 4.369274139404297, "identity": 0.5296041965484619, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a32f421b960f19d6df984793025b74cfba9839b1dfdc9f5fcd5a62076b2a280b.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "a361307e8238705c9c930118796a00d23a57da018088a8e18ae0f08a85bd2c7f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6eb49654bf374cffbd183d3c15433141d4a51c3bed206cf17578402b17b518a9", "generation_seconds_batch": 21.260343733010814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3657644987106323, "target_z": 2.2031251128523963, "ce": 6.109982967376709, "genuineness": 4.381826400756836, "identity": 0.03480914980173111, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a361307e8238705c9c930118796a00d23a57da018088a8e18ae0f08a85bd2c7f.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "a37381558bef9dcd2ca55fe129a69444fc4200195ec1cb8726519a1cddd999dc", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "27af326111361966889af881e50e7688090f4e3fec2d5feaa3fdf8ffe2215297", "generation_seconds_batch": 22.16006980894599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8986559510231018, "target_z": 1.3046875116435013, "ce": 6.054384231567383, "genuineness": 4.218649387359619, "identity": 0.7249118089675903, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a37381558bef9dcd2ca55fe129a69444fc4200195ec1cb8726519a1cddd999dc.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "a3e0433b7ad31a168b031c8bce7742636d84774fb2bc8fe3ecc5081d75cdbbd7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "21b3cd1f15b843a7ad6b9bcb006a3ee37f8012bd2a61b0a5dcc4db039e5920fd", "generation_seconds_batch": 18.769832844962366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6574208736419678, "target_z": 4.687499806538749, "ce": 6.395919322967529, "genuineness": 4.011539936065674, "identity": 0.3474271297454834, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a3e0433b7ad31a168b031c8bce7742636d84774fb2bc8fe3ecc5081d75cdbbd7.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "a4354af189b125110a66181085ee06be34dd93966f5ad67d879e66df6efe0135", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "d814225d5f14c3a04cd97aac1cde5a4a6297122c68025edb321255a16d2f571f", "generation_seconds_batch": 19.475732991006225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6249263286590576, "target_z": 4.624999727721203, "ce": 6.229123115539551, "genuineness": 3.7918784618377686, "identity": 0.39030173420906067, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinaus.", "wer": 0.0625, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a4354af189b125110a66181085ee06be34dd93966f5ad67d879e66df6efe0135.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "a448b9de0c804bcdbe9a1aa80ecb0c39fd6e0a6b426dd24bf88aa489043841b2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3516627e523e44b6ee589eba773d0a9dbd26266924c75d145a4a2a644f5f3e55", "generation_seconds_batch": 21.173416113015264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6305763125419617, "target_z": 0.7890625492609665, "ce": 6.062326908111572, "genuineness": 4.074300289154053, "identity": 0.6368744373321533, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a448b9de0c804bcdbe9a1aa80ecb0c39fd6e0a6b426dd24bf88aa489043841b2.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": "a48432730e2255b21ce6318d4712a8b86807ad5b5317b5fb0e80a2e4b05be99a", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7cb526d6e3aebbf14f9e638e1ec861a0709ddfe772144910baadb843514f0f07", "generation_seconds_batch": 19.631051381933503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8296051025390625, "target_z": 1.1718749587999189, "ce": 6.268836498260498, "genuineness": 4.068024158477783, "identity": 0.7674806118011475, "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_Pride/a48432730e2255b21ce6318d4712a8b86807ad5b5317b5fb0e80a2e4b05be99a.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "a49003876742d0160cb6819933ad69a8e510efe8af5301994baf7cfa71d30797", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1f4175047e13294ea840e4d8fb94d2c20aa661dbc53a4134b1644aaef26fb57c", "generation_seconds_batch": 21.489514266955666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5599374771118164, "target_z": 4.500000028660926, "ce": 6.23706579208374, "genuineness": 3.7542223930358887, "identity": 0.6370634436607361, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a49003876742d0160cb6819933ad69a8e510efe8af5301994baf7cfa71d30797.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": "a4e7d52a6f004e815e5ed27c0f111224b1b930f322ecbb777affea149dbc84d8", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The road turns left behind the bridge.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eda24e27ad52075576957e0abe6ff878285de7fdc7c3baebdbd2d4f45dcb5c5e", "generation_seconds_batch": 14.541702192043886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4650574028491974, "target_z": 0.4707031167152011, "ce": 6.395919322967529, "genuineness": 4.011539936065674, "identity": 0.2350424826145172, "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_Pride/a4e7d52a6f004e815e5ed27c0f111224b1b930f322ecbb777affea149dbc84d8.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "a5b049ab745769e9d8891cf62af3f3f1545d03080bba62276c72ca2daa7a62bf", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d18c7268db259f8e331824ecc80a43449abf0471d93839180966eb2e61e9248e", "generation_seconds_batch": 18.966965776053257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9758303761482239, "target_z": 1.4531249695477662, "ce": 6.070269584655762, "genuineness": 3.9801597595214844, "identity": 0.7002322673797607, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a5b049ab745769e9d8891cf62af3f3f1545d03080bba62276c72ca2daa7a62bf.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "a61dfecd8b3e6422231cdd5de17c66535e8ee7da849918f3f757659fe3cf293f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "02c689189c8e207a1fbc254f3c62bcdb2867253d559084cd80905a50c26e7010", "generation_seconds_batch": 20.91935714299325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6407307982444763, "target_z": 0.8085937092477459, "ce": 6.205295085906982, "genuineness": 4.15588903427124, "identity": 0.6796146035194397, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a61dfecd8b3e6422231cdd5de17c66535e8ee7da849918f3f757659fe3cf293f.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "a62b44d7be9da9265fb1eefd3f48276b309dde5dfa328c89eefe88171dbd664e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ac342e3ce78d1fa53559d1bb09d96b6d9a562d5c409f967b3b9c1ab5bf82b9e4", "generation_seconds_batch": 20.57273100502789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.955521285533905, "target_z": 1.4140624202867995, "ce": 5.871703147888184, "genuineness": 3.8922953605651855, "identity": 0.6711058616638184, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a62b44d7be9da9265fb1eefd3f48276b309dde5dfa328c89eefe88171dbd664e.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "a6854484e737492add1e92bfa6e2ca9e83d176bc4955f69e1942fad827e680b1", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4b8daf557440abb6c0dce61ab381f67f4fe3e00c9d843fc278c0e276da868468", "generation_seconds_batch": 21.404209358035587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8011724352836609, "target_z": 1.1171875044782698, "ce": 6.133810997009277, "genuineness": 4.20609712600708, "identity": 0.5311996936798096, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a6854484e737492add1e92bfa6e2ca9e83d176bc4955f69e1942fad827e680b1.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": "a6af9dac00f0898039462bfdd9a71c811fd794daabec68871ab50f7846186635", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The keys are on the kitchen table.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a618eea709beecde05a5fa3b7a8877b6a2e5916d9e65ecee6cfd64a0ddd0f119", "generation_seconds_batch": 18.54634471994359, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.624483585357666, "target_z": 0.7773437844826766, "ce": 6.3641486167907715, "genuineness": 3.998987913131714, "identity": 0.2889344394207001, "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_Pride/a6af9dac00f0898039462bfdd9a71c811fd794daabec68871ab50f7846186635.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "a6e093ac051b0c7c73f2981a5dc273058461accbe35483f5b50e52bf63e2c55d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0878855738ea681cf8582b9568850c9914a8c963ece2af23cfdc60b80489a87e", "generation_seconds_batch": 18.56874211190734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7889869809150696, "target_z": 1.0937499749216897, "ce": 5.689021587371826, "genuineness": 4.017816066741943, "identity": 0.5837281346321106, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay detrás.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a6e093ac051b0c7c73f2981a5dc273058461accbe35483f5b50e52bf63e2c55d.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": "a7c1cd36105c7f7e38c78b4a17e741dee6e67edb635c8e2be112a7c0b1acc31e", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "69fa83573075f8ffdab2523a70d95562dbb22cd6a62df5a1519265f11f596d33", "generation_seconds_batch": 13.766021937015466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41936200857162476, "target_z": 0.3828124955217303, "ce": 6.24500846862793, "genuineness": 4.344170093536377, "identity": 0.803550124168396, "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_Pride/a7c1cd36105c7f7e38c78b4a17e741dee6e67edb635c8e2be112a7c0b1acc31e.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "a7c535e24867f52251eafe14708bea0bba374cc6ae759abfa792d945ebcbe486", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "28a6ebcea5633d6b54c83a26ea323ddfaee2baa5efa7993f1e2e5c5af91e35f4", "generation_seconds_batch": 13.823449744959362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1058083772659302, "target_z": 1.70312494088684, "ce": 5.959072113037109, "genuineness": 3.9048471450805664, "identity": 0.4479037821292877, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a7c535e24867f52251eafe14708bea0bba374cc6ae759abfa792d945ebcbe486.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "a81c0f911eb8e6004bcd838eab475c1d17e761aafd880c4627f1f3065f03245d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ee840099a24e6ab43e51a1ea1afa983e2359fb4d231f2e8f1fe331f29c24121f", "generation_seconds_batch": 19.003130811965093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3817902207374573, "target_z": 0.3105468367107942, "ce": 6.141753673553467, "genuineness": 4.250029563903809, "identity": 0.6254048347473145, "hypothesis": "De deur staat nog open. ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a81c0f911eb8e6004bcd838eab475c1d17e761aafd880c4627f1f3065f03245d.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "a85f1265b749c0e5ace0ebb3450444530135b9471e75ca0901ff3b4e4e18ede7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3c8166aedd33f444404f2ee0ca37127409dfece2af1180874386e266ff4b17fa", "generation_seconds_batch": 13.865472316974774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6265144944190979, "target_z": 0.7812500394087732, "ce": 6.300607204437256, "genuineness": 4.111956596374512, "identity": 0.32586634159088135, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a85f1265b749c0e5ace0ebb3450444530135b9471e75ca0901ff3b4e4e18ede7.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "a4343729a0d0d8ac71af1bec47ec844d83ccc0de1535597da97ecaa9e689e2a0", "generation_seconds_batch": 14.993907129974104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5249691605567932, "target_z": 0.5859375223913484, "ce": 6.078212261199951, "genuineness": 4.042920112609863, "identity": 0.5244379043579102, "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_Pride/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "a8fc914835a66573c35e5a3c368d8dc9ec7318629b2632477871da910eaf1d47", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7dc91b02aedb52f9778504aaf197c316f7efe39f80ec2759dd57cf3ea0a0d335", "generation_seconds_batch": 20.556325014913455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.023778200149536, "target_z": 3.468750103895857, "ce": 6.0305562019348145, "genuineness": 4.068024158477783, "identity": 0.4772811532020569, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a8fc914835a66573c35e5a3c368d8dc9ec7318629b2632477871da910eaf1d47.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": "a91d33112ca3fd8d59b464f94b021b8127a16812ca2533e0c75b3f976cd8cbc4", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The road turns left behind the bridge.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "31ddd7c4d1c33235f9317f0c490950d3d72e4b4ee5cd950ceec59e885622a262", "generation_seconds_batch": 18.435051930951886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7686778903007507, "target_z": 1.0546874256607233, "ce": 6.4515180587768555, "genuineness": 3.9676074981689453, "identity": 0.2665852904319763, "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_Pride/a91d33112ca3fd8d59b464f94b021b8127a16812ca2533e0c75b3f976cd8cbc4.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "e5683c3fb18468df0b44af45f35baae7be283d5703e40e9f84b4200e414ac97d", "generation_seconds_batch": 14.417968613095582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6691635251045227, "target_z": 0.8632812782130991, "ce": 6.1894097328186035, "genuineness": 4.457139015197754, "identity": 0.7415972948074341, "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_Pride/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "a975889b74a6f2a8ea51e1d99c821741bb84a8af262eeb5ab3785dcd9a07ade1", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "b36e796f06e7b21ad2ed083eb719fea102e623ee877a8c96ae6ba675fc552bfa", "generation_seconds_batch": 21.409045887063257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3007755279541016, "target_z": 2.078125184504711, "ce": 5.863759994506836, "genuineness": 3.9676074981689453, "identity": 0.3919404149055481, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hace.", "wer": 0.11764705882352941, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/a975889b74a6f2a8ea51e1d99c821741bb84a8af262eeb5ab3785dcd9a07ade1.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": "a9b1fe17fe3571991633301907383276456a0995d43377fed1c34fba6c2f4230", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I wrote the number on the envelope.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "46de21f4cc32707c82551514d124a9710e34d537ffe9d5ce39caaf0aa04d9ec3", "generation_seconds_batch": 16.0765014749486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6419677734375, "target_z": 2.7343750949393173, "ce": 6.308549880981445, "genuineness": 3.9173994064331055, "identity": 0.3930550217628479, "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_Pride/a9b1fe17fe3571991633301907383276456a0995d43377fed1c34fba6c2f4230.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "aa4a65ebfbc7d07eabe52e141e5cb69d6de09c730ff8bc6c79cefb842fd79f67", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8288c9eb63a437de4ca750b9173eb112448bd318741c36619bf696baebb62611", "generation_seconds_batch": 19.12807909399271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.982365846633911, "target_z": 5.312499677564583, "ce": 6.3641486167907715, "genuineness": 3.7165660858154297, "identity": 0.4228302836418152, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschreiben.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/aa4a65ebfbc7d07eabe52e141e5cb69d6de09c730ff8bc6c79cefb842fd79f67.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "aa4eabed4896229a1124242221207cebb8ac753ef5cadcb5f101df7276fcff75", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8cb080408b2e42d6f51d19a79fcddba851a7fdbdf80a934c08abf26b5ff12fe7", "generation_seconds_batch": 18.893401367007755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8986559510231018, "target_z": 1.3046875116435013, "ce": 6.24500846862793, "genuineness": 4.494794845581055, "identity": 0.5910331010818481, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/aa4eabed4896229a1124242221207cebb8ac753ef5cadcb5f101df7276fcff75.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "aa5a18c1b24e99ff42f380eede99936353b289ea6c6a5be76718944d3ba6e2fb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "57d57ce5fea4e3691ba53932c3ae84d9ca40c87b8c2c75b4b1391aa27a4d93ec", "generation_seconds_batch": 18.6241760289995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3324759006500244, "target_z": 4.062499935512917, "ce": 6.300607204437256, "genuineness": 3.936227321624756, "identity": 0.6280663013458252, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/aa5a18c1b24e99ff42f380eede99936353b289ea6c6a5be76718944d3ba6e2fb.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "aa8916c29ba2420d15bf2dd4e85032fedd180ccb193a6cd1afd5142b43563d51", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5ed046a304764de4912566f2dd5f05f1cd48df38bd814a8658065760fc650f9d", "generation_seconds_batch": 18.774364633951336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.878346860408783, "target_z": 1.2656249623825346, "ce": 5.998785495758057, "genuineness": 3.9299514293670654, "identity": 0.6501102447509766, "hypothesis": "De deur 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_Pride/aa8916c29ba2420d15bf2dd4e85032fedd180ccb193a6cd1afd5142b43563d51.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "aad9a38230eeb65c81a9e86e6afa65ef02eb0483ea64be55cd4ec6bab98b8fe2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8920d37a48bb93763871c386dde035b00b3946df503786ea4927023e67c46a64", "generation_seconds_batch": 13.76709956000559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7443070411682129, "target_z": 1.0078124811912672, "ce": 6.205295085906982, "genuineness": 4.055472373962402, "identity": 0.6983004808425903, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/aad9a38230eeb65c81a9e86e6afa65ef02eb0483ea64be55cd4ec6bab98b8fe2.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": "aae4a2d331fafa104d596d2dd6a7a45624c3cdbdc33fb68316bdef5165c3d7f8", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "61a93cecf4a2d6ec32e713ab9fcf279eedc6962f525d581f8824568e151f2d5d", "generation_seconds_batch": 17.86131543200463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8092960715293884, "target_z": 1.1328125241826563, "ce": 6.38003396987915, "genuineness": 4.243753433227539, "identity": 0.40746408700942993, "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_Pride/aae4a2d331fafa104d596d2dd6a7a45624c3cdbdc33fb68316bdef5165c3d7f8.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "ab2d7eacf43ca86b8502cb1912fc90880c62ec4f8d1317565919aaa3ee0459cc", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9a745af2b29419bb79843e29f998512f320d53d7a696b61d0ad7eee9677e69d2", "generation_seconds_batch": 18.57332594797481, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49044376611709595, "target_z": 0.5195313032914093, "ce": 6.0146708488464355, "genuineness": 4.049196243286133, "identity": 0.672916054725647, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ab2d7eacf43ca86b8502cb1912fc90880c62ec4f8d1317565919aaa3ee0459cc.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "ab2ed56e3593ad08495d03c53c40b65299f7fdd5ef28450b2c25038ec606a04f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9d79aa3ff51997418de5d29a3d66687f97c027eacafbfde7b752c81da1170e19", "generation_seconds_batch": 18.80922235304024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4063825607299805, "target_z": 2.2812499820869214, "ce": 6.117925643920898, "genuineness": 3.9048471450805664, "identity": 0.1215626448392868, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ab2ed56e3593ad08495d03c53c40b65299f7fdd5ef28450b2c25038ec606a04f.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "ab627600ff77675c63c29fab2e95227a30c7be0c04c89cba8387be98e5da3762", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7ca1eb1a120990ae8c7b34ea3400d019c1a15efd108153dbed50aefd67c87979", "generation_seconds_batch": 19.51467111497186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9270886182785034, "target_z": 1.3593749659651504, "ce": 5.9431867599487305, "genuineness": 3.973883628845215, "identity": 0.40209752321243286, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ab627600ff77675c63c29fab2e95227a30c7be0c04c89cba8387be98e5da3762.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "ab6c92c4fe85cc71f65e8fb945c5eae7185ad0dd958f6b1252cb294f04e9550b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3c41c8eb59945159d53f52abeea6b9074a928a81cdf7152fdeadcd10e31eedbb", "generation_seconds_batch": 14.783225922030397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0798494815826416, "target_z": 5.499999914017222, "ce": 6.332377910614014, "genuineness": 3.9550557136535645, "identity": 0.44404780864715576, "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_Pride/ab6c92c4fe85cc71f65e8fb945c5eae7185ad0dd958f6b1252cb294f04e9550b.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "595367d1290c9500c38ea2ce5f9bf20a1e8aa08e6b5e9e0dc8820c50cec6e005", "generation_seconds_batch": 16.154242236050777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5696491003036499, "target_z": 0.6718750161217709, "ce": 6.427689552307129, "genuineness": 4.306513786315918, "identity": 0.45641449093818665, "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_Pride/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.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": "abb2ea47c1b4e4a10e7f3ce1d09fd8bc8902cf0953147f1797f10f58083c2bb9", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "892d74b621d30818b42ad7fc66fc1efd11363e05d819b42f8692ac5ccb30ea34", "generation_seconds_batch": 18.39796023501549, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1375088691711426, "target_z": 3.6874999211824533, "ce": 6.316492557525635, "genuineness": 4.250029563903809, "identity": 0.7224705815315247, "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_Pride/abb2ea47c1b4e4a10e7f3ce1d09fd8bc8902cf0953147f1797f10f58083c2bb9.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "abf434f465b790aa91dc65a1f63b651198da8102bbee3dbd74ec4fd8a3620ad9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cf14e61bf6d5b415427cc5e63a9b79de8e3377e674711dc8a41ecc2193381608", "generation_seconds_batch": 19.45364417496603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7483688592910767, "target_z": 1.0156249910434607, "ce": 6.205295085906982, "genuineness": 4.218649387359619, "identity": 0.7525576949119568, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/abf434f465b790aa91dc65a1f63b651198da8102bbee3dbd74ec4fd8a3620ad9.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": "ac071e7de9cd074299d6d7f15793500bcae39dca94e8df1c8371d2ad01dad71d", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Your message arrived after I had left.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c96ae3b5688154ed52449cdcc2fe05d48fa448b36ca35db3c7f5293ceb9c42fd", "generation_seconds_batch": 18.47389057802502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0367575883865356, "target_z": 1.5703125026869618, "ce": 6.372091293334961, "genuineness": 3.8922953605651855, "identity": 0.4266429543495178, "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_Pride/ac071e7de9cd074299d6d7f15793500bcae39dca94e8df1c8371d2ad01dad71d.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "ac87b9514c5d9b104c7f2d7cde12c07207a54dbb11331a410dc32c96c1d2750a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4c46e006a68ec37bfe63961b604721f421b2d5a9ebea5f266ca43e80be5b4aea", "generation_seconds_batch": 14.946834212983958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3738881349563599, "target_z": 2.218750132556783, "ce": 6.308549880981445, "genuineness": 4.080576419830322, "identity": 0.4734157919883728, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ac87b9514c5d9b104c7f2d7cde12c07207a54dbb11331a410dc32c96c1d2750a.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "acdca89f1723d403f0468e5a507a4ae3cceba26d7895643b892bd2e179cb0f63", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5e91d00d5c6c70b8cc82f714eff9e256680f9740684acfffee38872fa7b2c847", "generation_seconds_batch": 14.660800334997475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0002013444900513, "target_z": 1.50000014330463, "ce": 5.879645347595215, "genuineness": 3.986435890197754, "identity": 0.4276731610298157, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/acdca89f1723d403f0468e5a507a4ae3cceba26d7895643b892bd2e179cb0f63.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "ad307473130c2694a87626c224ce757992d9edac74b6c524793f301b80759d3d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "878aeb38e3aa12fbe50f73da9ed1732c9f87e2bb659c5b227b873fe1b45898d0", "generation_seconds_batch": 19.422576512093656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.998613119125366, "target_z": 5.343749716973356, "ce": 6.260893821716309, "genuineness": 4.036643981933594, "identity": 0.4494935870170593, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ad307473130c2694a87626c224ce757992d9edac74b6c524793f301b80759d3d.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "ad323743ee21969a9ab5c39e265b915a140043c90c19b40bc5b1584d2d6701cb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "01b43b1a900a0dfab6261c00cb3d8eb8e5dc72aed702cac6e4dce772fa15bfac", "generation_seconds_batch": 18.57746955100447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.878346860408783, "target_z": 1.2656249623825346, "ce": 6.252951145172119, "genuineness": 4.055472373962402, "identity": 0.712203323841095, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ad323743ee21969a9ab5c39e265b915a140043c90c19b40bc5b1584d2d6701cb.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "ad3e2695c3b5403c77fd5750747207217f521ae88318ab651317a5612bff633b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1cbcc0695e09802f793906227cb7a678dbb9ba400ac2836b125cc5c5687809e5", "generation_seconds_batch": 17.021484562079422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.203291893005371, "target_z": 1.8906249480520716, "ce": 6.070269584655762, "genuineness": 3.8922953605651855, "identity": 0.5331156253814697, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ad3e2695c3b5403c77fd5750747207217f521ae88318ab651317a5612bff633b.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "ada07d14b38822699191bba5c60d2d81dc5c3ff06a06d42405f6aec487531ca1", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8c68040c94316665b125370efabc09c357ef0de1038a629c2a69b85407d83c4c", "generation_seconds_batch": 16.410026705940254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1870447397232056, "target_z": 1.8593751379307064, "ce": 6.205295085906982, "genuineness": 4.419482707977295, "identity": 0.5787343382835388, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ada07d14b38822699191bba5c60d2d81dc5c3ff06a06d42405f6aec487531ca1.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "f56c7ab1ed14828f123fa46d966783de49be79e41cc6d192691bbe1e7ebb4acb", "generation_seconds_batch": 14.535842639044859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3381257653236389, "target_z": 0.22656252776527205, "ce": 6.165581703186035, "genuineness": 4.356721878051758, "identity": 0.6200591325759888, "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_Pride/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "adefb7c32558a20049f2843874a46e236019e2aa8989e8ae381e01a4954f168b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e31fcedd09bc11b618c418c8d5163be7810933930304f6128c6db57d06441967", "generation_seconds_batch": 19.22178163798526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.991283655166626, "target_z": 3.40625002507831, "ce": 6.292664527893066, "genuineness": 4.13078498840332, "identity": 0.47287505865097046, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/adefb7c32558a20049f2843874a46e236019e2aa8989e8ae381e01a4954f168b.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "ae0a6b6dc7cbacfab54b8d04afa032d2e8cae0434ab92a408fa167aa0fc30e61", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6dcd9939ec0ef1e73f9def80d6135610a34af4cb816c945762aa0a272cba50f6", "generation_seconds_batch": 18.463542485958897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1383029222488403, "target_z": 1.7656250197043866, "ce": 5.959072113037109, "genuineness": 3.9801597595214844, "identity": 0.6194126605987549, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ae0a6b6dc7cbacfab54b8d04afa032d2e8cae0434ab92a408fa167aa0fc30e61.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "9678e8421c38e8c055142018d2c7d038d81887dd57dced9e59554526ea18eb08", "generation_seconds_batch": 14.143004130921327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47622740268707275, "target_z": 0.4921875188087327, "ce": 6.38797664642334, "genuineness": 4.13078498840332, "identity": 0.10056843608617783, "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_Pride/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "ae5a9c81fb0019f62d1d45cfb0cd5e87f0870ac06a9079a5e7bab729fe83bb7a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f05ca334a7737c9e927b4144b17b059cb0019cfefc1708f5000aea67e9de2e85", "generation_seconds_batch": 20.780075344024226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5696491003036499, "target_z": 0.6718750161217709, "ce": 6.125868320465088, "genuineness": 4.118232727050781, "identity": 0.721300482749939, "hypothesis": "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_Pride/ae5a9c81fb0019f62d1d45cfb0cd5e87f0870ac06a9079a5e7bab729fe83bb7a.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": "ae9dd6a24dc025ec9f49c3bb4e9e673ca0b9dbf07e27ace43e75f7b016c44e7c", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34d85f2000f2d976df7d2cdf02ff149730f7a9a7fd3cc63e748dc74a21cbe800", "generation_seconds_batch": 14.681333899032325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9100474119186401, "target_z": 3.250000057321852, "ce": 6.125868320465088, "genuineness": 4.055472373962402, "identity": 0.5466384887695312, "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_Pride/ae9dd6a24dc025ec9f49c3bb4e9e673ca0b9dbf07e27ace43e75f7b016c44e7c.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": "aead68496219c96e92e65dac07716c159094e372bcb43eed368aba35d3fc8398", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d695ee5664457bb55a2cedb3d8c990491489fdcaa00b149d3be79ae9a1f71176", "generation_seconds_batch": 13.839385398081504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8499141931533813, "target_z": 1.2109375080608855, "ce": 6.3641486167907715, "genuineness": 4.137060642242432, "identity": 0.4520925283432007, "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_Pride/aead68496219c96e92e65dac07716c159094e372bcb43eed368aba35d3fc8398.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "af0bc3ca469db566583ded959ec23629272e230513ea9a896b7cad26b2e7dfdf", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9e69aeec3bed5a41b81363ad7ef98dd0bb4c7ddaf846780158775bf5fa6782a2", "generation_seconds_batch": 13.823449744959362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6305763125419617, "target_z": 0.7890625492609665, "ce": 6.046441555023193, "genuineness": 4.055472373962402, "identity": 0.5418208241462708, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/af0bc3ca469db566583ded959ec23629272e230513ea9a896b7cad26b2e7dfdf.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "af3f04fa8ecb4ad122ff547a0fd044af52176a2004a494b6d88c1a465fcaf6a3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "088dbe3c04167de25fb758f2039cc7efeacb23497a021c8737ff5f59884c5289", "generation_seconds_batch": 22.38175440998748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.853182077407837, "target_z": 3.1406251486785535, "ce": 6.054384231567383, "genuineness": 4.331617832183838, "identity": 0.5440692901611328, "hypothesis": "J'ai trouvé la 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_Pride/af3f04fa8ecb4ad122ff547a0fd044af52176a2004a494b6d88c1a465fcaf6a3.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": "afb5d4c2e113a4aa9d6e7ba7997c3ceb6d8da40b989e34d1a483c90b07630704", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Someone moved the little blue chair.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fad2d5f4c03795076d842103035d5903d64a1cb0d3863fe54e4c8a2e173b171", "generation_seconds_batch": 19.438986046006903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4467792510986328, "target_z": 0.4355468797021832, "ce": 6.427689552307129, "genuineness": 4.193545341491699, "identity": 0.2499694675207138, "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_Pride/afb5d4c2e113a4aa9d6e7ba7997c3ceb6d8da40b989e34d1a483c90b07630704.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "afdec7f13ad9481333bf5b40292b9535af312162d16ae4d2a2b7b3228951fdaf", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ecb8aed2fb9812902b8db86c43ceaa82d66d6e25b44ca10179adbbd1ae840651", "generation_seconds_batch": 18.454116067034192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5798036456108093, "target_z": 0.6914062907522541, "ce": 5.982900142669678, "genuineness": 4.086852550506592, "identity": 0.6394124031066895, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/afdec7f13ad9481333bf5b40292b9535af312162d16ae4d2a2b7b3228951fdaf.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": "b05ecac8262f542b8f5be781c56a922fdcee1943627663a8009117730bc96951", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The keys are on the kitchen table.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c592c0105edeefa382021f9160c44bb32da89256eade0c4169374d05aeb7d68", "generation_seconds_batch": 16.472860377980396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4630264937877655, "target_z": 0.4667968617891044, "ce": 6.308549880981445, "genuineness": 3.9927117824554443, "identity": 0.3240324854850769, "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_Pride/b05ecac8262f542b8f5be781c56a922fdcee1943627663a8009117730bc96951.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "b081a721a9321d1a45b4d082d96392dbb57c1cd0bff205dd947afb9bc8c150cf", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "80da2bee03108731272ae1266918def08bad01514ce53cee0cbec018aeeff98a", "generation_seconds_batch": 21.95960490894504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0083248615264893, "target_z": 1.5156249337216086, "ce": 6.300607204437256, "genuineness": 4.231201171875, "identity": 0.42162781953811646, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b081a721a9321d1a45b4d082d96392dbb57c1cd0bff205dd947afb9bc8c150cf.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "b0ab642f1af32d077271197ce5b2a60de5567c5ce19935a2fd7aa3c6fa81359a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ddb2f7b44ee8733b5666ac36cc6d74ec027622d138bb4a5537b64718dc8853e2", "generation_seconds_batch": 18.62059354002122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.780863344669342, "target_z": 1.0781249552173031, "ce": 6.125868320465088, "genuineness": 4.243753433227539, "identity": 0.43353271484375, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b0ab642f1af32d077271197ce5b2a60de5567c5ce19935a2fd7aa3c6fa81359a.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "b0c22a0c53755a42c583f3dd862b4edffa44c1d3fa7517c8fc884c4196fa18e4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2cfff05744b5c4f91d105854e1ced68a441af1104bd2d7d29f98ce60bac30129", "generation_seconds_batch": 22.508836121996865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0473549365997314, "target_z": 5.4374998351996755, "ce": 6.09409761428833, "genuineness": 4.093128204345703, "identity": 0.26728877425193787, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b0c22a0c53755a42c583f3dd862b4edffa44c1d3fa7517c8fc884c4196fa18e4.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": "b1ac8c8a4bb4e10906957d1c8fc5bb6ddb89387d18e4205bec9b8618c3d93d28", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "63cdf12f370af52316a12015f790245ef4485adfddcc96878fae96c42ad32d94", "generation_seconds_batch": 19.12821916898247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7402452230453491, "target_z": 0.999999971339074, "ce": 6.23706579208374, "genuineness": 3.9927117824554443, "identity": 0.7617366313934326, "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_Pride/b1ac8c8a4bb4e10906957d1c8fc5bb6ddb89387d18e4205bec9b8618c3d93d28.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "b20d128d32d0192502b584dfb0e39ff5ad789f01a1ec1cfe7fed2ac4f3c79b1b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e06325a26d1e90a933e5342d12ffa70ebf0680f9855a9934381c0673ec7ef64", "generation_seconds_batch": 20.343839989043772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3007755279541016, "target_z": 2.078125184504711, "ce": 6.0146708488464355, "genuineness": 4.344170093536377, "identity": 0.6255937218666077, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b20d128d32d0192502b584dfb0e39ff5ad789f01a1ec1cfe7fed2ac4f3c79b1b.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "b22b5cbcd33b08d0377e465105a870aa87f8b1f55376f2fa5256117663f91b4a", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fbfae1287a45f8c888d7dcf58ed700442050ccae0c84b6e21078316e3dff3450", "generation_seconds_batch": 16.410026705940254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7321215867996216, "target_z": 0.9843749516346874, "ce": 6.1020402908325195, "genuineness": 4.532451152801514, "identity": 0.6593000292778015, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b22b5cbcd33b08d0377e465105a870aa87f8b1f55376f2fa5256117663f91b4a.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "b2663bffa7e5a4bd7d5541eab5c90591ab33865b0a9b646b4260beb7aba78eb3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d33fc9d2503a645eecf0f70dd091e2380a7a56366af63c0ef255ad95b268cb26", "generation_seconds_batch": 21.474003519047983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6346380710601807, "target_z": 0.7968749444694558, "ce": 6.070269584655762, "genuineness": 4.017816066741943, "identity": 0.6326230764389038, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b2663bffa7e5a4bd7d5541eab5c90591ab33865b0a9b646b4260beb7aba78eb3.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "b26b7b2e8bcaa8c2e7c509d18eacbde50ac70216af97aa3fbeb900e6647a68e0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6b8c632dd92346242dd300f5c3c1bb79af1c677d68f32c9bdfb088c728965bac", "generation_seconds_batch": 24.218496663030237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6907094717025757, "target_z": 2.828124983878229, "ce": 5.839932441711426, "genuineness": 4.13078498840332, "identity": 0.6424722671508789, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b26b7b2e8bcaa8c2e7c509d18eacbde50ac70216af97aa3fbeb900e6647a68e0.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "b307c738bb35bc8667204935a2276870ab9bc7c9050e90ac5d244eca7e6ad501", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2d98909282d687f46bb63ed7b31356f957af92f5b7529f811e607cbdf8f7b616", "generation_seconds_batch": 22.03461676905863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5005982518196106, "target_z": 0.5390624632781885, "ce": 6.24500846862793, "genuineness": 4.306513786315918, "identity": 0.6130204200744629, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b307c738bb35bc8667204935a2276870ab9bc7c9050e90ac5d244eca7e6ad501.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": "b33310e8f97fcb5a761a717a9a1e56d5dd466303e2ad3fe6ae2afd982451d994", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fed5e27ff3bc084cba05ff72dec856b0a5105c4199c691bf88437afaebe00058", "generation_seconds_batch": 13.924845490022562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.51075279712677, "target_z": 0.5585937379086718, "ce": 6.173524379730225, "genuineness": 4.005263805389404, "identity": 0.6027272343635559, "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_Pride/b33310e8f97fcb5a761a717a9a1e56d5dd466303e2ad3fe6ae2afd982451d994.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "b36bf8d060ea6bef06d123cbb417d7482460d012b88558203f32d60d83a2d5a4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "7f58ed55a3e5d3cbb0c2d3b3bbb15008b7572a8f5562751126aeca38b5545916", "generation_seconds_batch": 19.93559719400946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8336669206619263, "target_z": 1.1796874686521122, "ce": 6.149696350097656, "genuineness": 4.030367851257324, "identity": 0.4534321129322052, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b36bf8d060ea6bef06d123cbb417d7482460d012b88558203f32d60d83a2d5a4.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "b3c9ba802a96ce543d1155c3bba6507c7ab11fdf5d9321b28c2ef9322bdf527d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d6c732b358303eba64b681350c3bf7c561038c20f0f74f681e20da60e492e64a", "generation_seconds_batch": 18.70184497802984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9149031639099121, "target_z": 1.3359374364085705, "ce": 5.990842819213867, "genuineness": 4.118232727050781, "identity": 0.35490256547927856, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "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_Pride/b3c9ba802a96ce543d1155c3bba6507c7ab11fdf5d9321b28c2ef9322bdf527d.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "f800cfe10cd170a920165fc49e44d48f5ae2c919321f96444423d403028f4abf", "generation_seconds_batch": 16.504361557075754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21627135574817657, "target_z": -0.007812509852193311, "ce": 6.443574905395508, "genuineness": 4.545003414154053, "identity": 0.5759302973747253, "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_Pride/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "b450efc56922e97d0e125df89db867c7359c9decc3e254b5269804c234cb5f61", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f5bd84468ec342483e7a0db33bd2bf84a12e6c6273c2afed8472b0d4a2262df5", "generation_seconds_batch": 19.437839750084095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.894594132900238, "target_z": 1.2968750017913078, "ce": 6.086154937744141, "genuineness": 4.425758361816406, "identity": 0.7859121561050415, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b450efc56922e97d0e125df89db867c7359c9decc3e254b5269804c234cb5f61.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "b47407c32835649735feb978c644ac96d117099c07107f074b73f0338430892d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0e996c67e15ff363375056a25f49cddd0928a320be2c48a7529f44d53b0fd866", "generation_seconds_batch": 19.52123998303432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5274429321289062, "target_z": 4.43749994984338, "ce": 6.340320587158203, "genuineness": 4.13078498840332, "identity": 0.6329220533370972, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b47407c32835649735feb978c644ac96d117099c07107f074b73f0338430892d.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "b56e45a0eebf67a8c7bf2e9814e8bdb656cd4f495418008779161c756d5727e2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a4961b323480a3aae2fe5a816088771132a74727b048e06115be13c5e5679b49", "generation_seconds_batch": 20.372071170946583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1870447397232056, "target_z": 1.8593751379307064, "ce": 6.006728172302246, "genuineness": 4.20609712600708, "identity": 0.49299246072769165, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre.", "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_Pride/b56e45a0eebf67a8c7bf2e9814e8bdb656cd4f495418008779161c756d5727e2.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": "b5dbe631f42cb23e092da5ea213fbb09cd6987504480905ee9a44c7644d9364c", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "11d2c190cace4e9b11b9149ce8f55781453e62e1bf164e28f6602fbcd6b375d3", "generation_seconds_batch": 14.82747878599912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5026291608810425, "target_z": 0.5429687182042853, "ce": 6.117925643920898, "genuineness": 3.9676074981689453, "identity": 0.7647823691368103, "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_Pride/b5dbe631f42cb23e092da5ea213fbb09cd6987504480905ee9a44c7644d9364c.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "b696233b4b792cc7c7fc6dad3c54399a30b3c9f64ac221242788833e59111819", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "19a96a067d5ea7f0eec8e6c8734cc8680a6b141ae6349d934802f08a388c2496", "generation_seconds_batch": 18.40992855501827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.14563250541687, "target_z": 3.7031249408868403, "ce": 6.316492557525635, "genuineness": 3.9927117824554443, "identity": 0.5877705812454224, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschreiben.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b696233b4b792cc7c7fc6dad3c54399a30b3c9f64ac221242788833e59111819.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "b6a08d1a36bd74499bce43133f01a7322dc9d1e2a390708bf71e111fa9fdbd93", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f031859d32d1c8bd8d4a7ed8e7a6d3619418d7298ddc320f0906c70d49c2d9cb", "generation_seconds_batch": 18.514910822967067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0319018363952637, "target_z": 3.4843751236002434, "ce": 6.109982967376709, "genuineness": 4.005263805389404, "identity": 0.31704777479171753, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b6a08d1a36bd74499bce43133f01a7322dc9d1e2a390708bf71e111fa9fdbd93.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "b6ad873eedc67860369f348d6fce4c55aea392e19c2b044b11f76d478313e881", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b945b83497ef6d7573d89441984b73c7daba2132df192686cac647d4e481b054", "generation_seconds_batch": 20.53687378705945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25739720463752747, "target_z": 0.07128903775755997, "ce": 6.109982967376709, "genuineness": 4.432034492492676, "identity": 0.661268949508667, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b6ad873eedc67860369f348d6fce4c55aea392e19c2b044b11f76d478313e881.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "b6e4733dd828ce7e8be42cc5b53c83372a09ca9d3f04b874f2db7d5e43ce5ea2", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "040ac6a689baca2ccd200ec6575cc828a81adb8966e3158ea4962c350ace95da", "generation_seconds_batch": 17.331555669079535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9677067399024963, "target_z": 1.4374999498433796, "ce": 6.221180438995361, "genuineness": 4.193545341491699, "identity": 0.6328891515731812, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b6e4733dd828ce7e8be42cc5b53c83372a09ca9d3f04b874f2db7d5e43ce5ea2.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "b74cbe23ec3a67628efd301e0c6555fe8b0eb8cf8b246783c03afa29bb8e10f4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2e259d28f1098fa239fbf92328332c1fa0954cdd5ee2925368f9e4e4999b37e5", "generation_seconds_batch": 16.544644084060565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7800694704055786, "target_z": 3.000000200626482, "ce": 6.324435234069824, "genuineness": 4.306513786315918, "identity": 0.48194700479507446, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b74cbe23ec3a67628efd301e0c6555fe8b0eb8cf8b246783c03afa29bb8e10f4.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": "b7a8068ecdaef154e3ea26092a3dca50d42ff559d257550b248beb2896465a4c", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb9e976c9d9328f5dad526469354718aa2058b38b3248ac715f46c3eb3da142b", "generation_seconds_batch": 14.911178280017339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7219670414924622, "target_z": 0.9648436770042041, "ce": 6.054384231567383, "genuineness": 3.8797430992126465, "identity": 0.42421531677246094, "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_Pride/b7a8068ecdaef154e3ea26092a3dca50d42ff559d257550b248beb2896465a4c.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "b7ca46e9ee2de10dc53bdbca13d3bcc4d3af31673b8f15b02f1a1627971b116c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8261c28c151270309502931224558954333f83f84f534694ed4e85709c32944c", "generation_seconds_batch": 16.914572459994815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.404130220413208, "target_z": 0.35351564089785736, "ce": 5.808161735534668, "genuineness": 3.9676074981689453, "identity": 0.6583235859870911, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b7ca46e9ee2de10dc53bdbca13d3bcc4d3af31673b8f15b02f1a1627971b116c.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "b807fbd5049a39f0be54032cd2c859a91bcca0c52027755e1d7b165af931f5c1", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "db1c1d1715b0eeb76cb97a40ba94f01756c3ad06063b0b9d18742e3409ee6192", "generation_seconds_batch": 19.11961476597935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.992077648639679, "target_z": 1.4843750089565393, "ce": 6.165581703186035, "genuineness": 3.8295347690582275, "identity": 0.21896979212760925, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b807fbd5049a39f0be54032cd2c859a91bcca0c52027755e1d7b165af931f5c1.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "b80e8275c863c79921eeb0c7622dea87db2be2d21d8109308dff8c36a0309781", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "09087f7b6f1da9368fb51276d9f95aff69a2949d9d0281b9e48ffcb67513858d", "generation_seconds_batch": 18.811872706981376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2560955286026, "target_z": 1.9921875761305847, "ce": 6.324435234069824, "genuineness": 4.243753433227539, "identity": 0.7423588037490845, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b80e8275c863c79921eeb0c7622dea87db2be2d21d8109308dff8c36a0309781.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "b8667d2a09c99cce886f13bef80734d61e68d17db60345b927778864b8bf16f4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "42fcf443866d83b498d58a7bfa1dd6d6d41a152192ef1ec1af5e7da905688012", "generation_seconds_batch": 19.11961476597935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.390135407447815, "target_z": 2.250000171965556, "ce": 6.1894097328186035, "genuineness": 3.835810661315918, "identity": 0.25206413865089417, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b8667d2a09c99cce886f13bef80734d61e68d17db60345b927778864b8bf16f4.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "b91368492b46109a97c2ca874a484e1d6aa840814c2521c35368f825b6214247", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "70e2f2c37972abced442f4c8fb3c5093093dd0b0055cd2c23d7e827098235a07", "generation_seconds_batch": 16.346996868029237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0326957702636719, "target_z": 1.5624999928347685, "ce": 6.23706579208374, "genuineness": 3.8922953605651855, "identity": 0.3258800506591797, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b91368492b46109a97c2ca874a484e1d6aa840814c2521c35368f825b6214247.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "b915322b5be31574fdc4731dcb1b732d9c96543a804de257d06ee5f9a40ab305", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "12b7e1a1b00da456c7e896ffde3a6af26d43b5bb51f333a87b1359a582e1e2ed", "generation_seconds_batch": 21.931552411057055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0570666790008545, "target_z": 1.6093750519479284, "ce": 6.109982967376709, "genuineness": 4.20609712600708, "identity": 0.5019456744194031, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b915322b5be31574fdc4731dcb1b732d9c96543a804de257d06ee5f9a40ab305.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "b92305b8b53918e3acee283df784a7c15569c95d6b0c4efd508c839b6e6962bb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7a9245d4456299e0e94ca11db8c4cf93eb4c880c5b085b5b24b5dee95eae8a8c", "generation_seconds_batch": 20.70100660691969, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5038660764694214, "target_z": 2.468749989252153, "ce": 6.260893821716309, "genuineness": 4.15588903427124, "identity": 0.4709130525588989, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b92305b8b53918e3acee283df784a7c15569c95d6b0c4efd508c839b6e6962bb.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "b9398b5e6e781ce4531a4ac74b73638f5457b7c9ed59338715129e97a8dd6ef0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "55a246be2bf60aea88adaf3a0af879cf68517f316616a3188338fa7ce659228c", "generation_seconds_batch": 19.50572011305485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9798921942710876, "target_z": 1.4609374793999594, "ce": 6.300607204437256, "genuineness": 3.9676074981689453, "identity": 0.2751754820346832, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b9398b5e6e781ce4531a4ac74b73638f5457b7c9ed59338715129e97a8dd6ef0.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "b9adc2b8a994c9893b384d06c7a10dd490baa46897ad566681aa74a505f5980c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f68fc5a79a3f5f453fb120b8edcc5b300e631f782a6a6d29a305873530012119", "generation_seconds_batch": 21.697387842927128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1212615966796875, "target_z": 3.65624988177368, "ce": 6.149696350097656, "genuineness": 3.9048471450805664, "identity": 0.615654468536377, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b9adc2b8a994c9893b384d06c7a10dd490baa46897ad566681aa74a505f5980c.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "b9b3015784f06ba4e12b335179eb5ca41632f310301a7812d4aecc0c7fa7ed12", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "be07f357ff2c8347a393ac625b992308ca00a5a16e100c830ddd383817de2297", "generation_seconds_batch": 20.90412747801747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1220556497573853, "target_z": 1.7343749802956134, "ce": 6.1894097328186035, "genuineness": 3.898571252822876, "identity": 0.1761934757232666, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b9b3015784f06ba4e12b335179eb5ca41632f310301a7812d4aecc0c7fa7ed12.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "b9c9997a64bbfcf717344625e481deb402be31876f33456b0afa7bf081364e77", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b40f294e93822baa6382964b4b264c9409082626a6551cb1a4cc7fe3df32c58c", "generation_seconds_batch": 20.556325014913455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.764616072177887, "target_z": 1.04687491580853, "ce": 6.292664527893066, "genuineness": 4.306513786315918, "identity": 0.6209550499916077, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/b9c9997a64bbfcf717344625e481deb402be31876f33456b0afa7bf081364e77.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "ba1ae5021cbd3821fb79fbe4a16c7a77f3129c6af2812dbb10ce3248cac531e4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c57aa936e075085a939b37f57550d1f141f951377e6e652e52abc7172d18f38c", "generation_seconds_batch": 14.261693430016749, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3007755279541016, "target_z": 2.078125184504711, "ce": 5.990842819213867, "genuineness": 4.030367851257324, "identity": 0.6331890225410461, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ba1ae5021cbd3821fb79fbe4a16c7a77f3129c6af2812dbb10ce3248cac531e4.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "ba36e30a92031c54f90a221d7f5fc593870160e8869faf50888705ac39fee25b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5925520b2fdc0671731b0c3a6c20ad1e27d02212a6c7213d7cb6b44659fbbcc5", "generation_seconds_batch": 21.84047155699227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0326957702636719, "target_z": 1.5624999928347685, "ce": 6.038498878479004, "genuineness": 3.9550557136535645, "identity": 0.590928852558136, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ba36e30a92031c54f90a221d7f5fc593870160e8869faf50888705ac39fee25b.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "ba5289335d41bac98631b46443f9fc4468adefc55d6f9c7754a7ec26a7dd02f3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "22dc1ed703a2dec87cf1dd6d81695ea5a5132e56948038163344e2f2897513ea", "generation_seconds_batch": 15.241453648079187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.87755286693573, "target_z": 3.1874999785043054, "ce": 6.300607204437256, "genuineness": 4.21237325668335, "identity": 0.4868299067020416, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ba5289335d41bac98631b46443f9fc4468adefc55d6f9c7754a7ec26a7dd02f3.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "de84172303c551d083a77b59ec154301dcd9192c79406acd7ebb9e51aaed039b", "generation_seconds_batch": 14.37251830601599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4396710693836212, "target_z": 0.4218749874608449, "ce": 6.173524379730225, "genuineness": 4.595211505889893, "identity": 0.734378457069397, "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_Pride/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.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": "ba86a88846dd3d4a16db6c29eebf84df2d70483eefef12ac1b94d80268ff91fc", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Escribí el número en el sobre.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fc153fde595b37213e3ac5fda5a35061019745435667a8a367d83ee4db955004", "generation_seconds_batch": 22.280046370928176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.511195659637451, "target_z": 4.406249910434607, "ce": 6.221180438995361, "genuineness": 4.281409740447998, "identity": 0.7096347808837891, "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_Pride/ba86a88846dd3d4a16db6c29eebf84df2d70483eefef12ac1b94d80268ff91fc.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "ba9d32ca6d302abda25bd747472a4090d29bfd5ab5622c58d9c5000033c036ef", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "42eb50ed8b9ee8b1144cb52c0041a9f86cdad306b4cb5a6423f14ebd39794ad8", "generation_seconds_batch": 22.359814755036496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7280597686767578, "target_z": 0.9765624417824941, "ce": 6.2767791748046875, "genuineness": 4.231201171875, "identity": 0.465260773897171, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay detrás.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ba9d32ca6d302abda25bd747472a4090d29bfd5ab5622c58d9c5000033c036ef.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "baeac09d6195af4874d33d8f2173ec9f7d33a8d056e17a514d811946f03424a7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2125d0ba8f3a9961cdad077e5bc2cdce5804f54d79516ad5c6be587594031d8c", "generation_seconds_batch": 13.910683244932443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7321215867996216, "target_z": 0.9843749516346874, "ce": 6.300607204437256, "genuineness": 4.068024158477783, "identity": 0.3148854970932007, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/baeac09d6195af4874d33d8f2173ec9f7d33a8d056e17a514d811946f03424a7.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "bb125d131d9ffc4bde91ab34bb061958e0e5d850fe496f2671f7a132b4171636", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "14e34a15d3a9a686974d41c02fd117eb155fe6e01373b53fbe82ead25a58b83e", "generation_seconds_batch": 19.440815508016385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5818345546722412, "target_z": 0.6953125456783508, "ce": 6.062326908111572, "genuineness": 3.8044304847717285, "identity": 0.7575525045394897, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/bb125d131d9ffc4bde91ab34bb061958e0e5d850fe496f2671f7a132b4171636.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "bb1474eb8294c862bf7500b6b5a6c12fd096e468f8ff452e75537ee63911f99e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "848c8246cf2f9beea41cc61a2ad1b9a1295e5ee657b67e46997276acc3f0fd42", "generation_seconds_batch": 14.086009127902798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2601573467254639, "target_z": 2.000000085982778, "ce": 5.784333229064941, "genuineness": 4.042920112609863, "identity": 0.6388503313064575, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/bb1474eb8294c862bf7500b6b5a6c12fd096e468f8ff452e75537ee63911f99e.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "bba1c25e05bc33d21bdaf8968155a26ca612d1dd26b6e0a0d2c89076283c59ba", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "35959418cd21aaec5a33e0a164c49807f10043c3fda57c0ac6f3e18c9d2e2fca", "generation_seconds_batch": 18.616662285057828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.663070797920227, "target_z": 0.851562513434809, "ce": 6.141753673553467, "genuineness": 4.193545341491699, "identity": 0.6098016500473022, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/bba1c25e05bc33d21bdaf8968155a26ca612d1dd26b6e0a0d2c89076283c59ba.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "bc7f8ccfd3b9aa36e4279d378303be7eb7c964c4748cc8bceb53d1edfaab39b4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "958f23ad781a383b89554594b6823edbfb9085c57f3391a2d2779ae0ceb65871", "generation_seconds_batch": 18.550568151054904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3982590436935425, "target_z": 2.2656251916699426, "ce": 6.1020402908325195, "genuineness": 4.143336772918701, "identity": 0.707731306552887, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/bc7f8ccfd3b9aa36e4279d378303be7eb7c964c4748cc8bceb53d1edfaab39b4.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "bcc03cb73065cedf4e386fbe41af1756123176fba5285fea58373032a430bb27", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bdc2b1b271274e4bd3883b6755d742ecb1ef0ac3a170d5c684fa33e37d1ca545", "generation_seconds_batch": 19.6449616139289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0367575883865356, "target_z": 1.5703125026869618, "ce": 6.205295085906982, "genuineness": 3.8922953605651855, "identity": 0.43272554874420166, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/bcc03cb73065cedf4e386fbe41af1756123176fba5285fea58373032a430bb27.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "bd5834a98293dd00db106b8f2ba9b4cb183d5923c7f903d178cbcc383d4550c1", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2f85f31ff8210a513f31b6cc0f0f9fa79eb632046b9ed380d0117d28d862a338", "generation_seconds_batch": 18.523253292078152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3162286281585693, "target_z": 4.031249896104144, "ce": 6.078212261199951, "genuineness": 4.143336772918701, "identity": 0.16791492700576782, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/bd5834a98293dd00db106b8f2ba9b4cb183d5923c7f903d178cbcc383d4550c1.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "bd5de039e870f4f0edbdb87e4e57e3d0253273aca8b045b8d3c40a95df05a298", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "674ab6cd327cd0a26dc0e830023488080797b1d2cda4de9706b61bcd92c6dc49", "generation_seconds_batch": 15.113008160958998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6549471616744995, "target_z": 0.8359374937304225, "ce": 5.967014789581299, "genuineness": 4.306513786315918, "identity": 0.6868722438812256, "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_Pride/bd5de039e870f4f0edbdb87e4e57e3d0253273aca8b045b8d3c40a95df05a298.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "bd6b418cac4be5aa191aa0595f24f2e8fe9002e29ce4e78147834db7ff702c5d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1d115c572616eed2108728c6e2106fc23c8eb79ec09ebb303c8fb524c62e7af", "generation_seconds_batch": 19.04155124805402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0481491088867188, "target_z": 3.5156251630090165, "ce": 6.268836498260498, "genuineness": 4.030367851257324, "identity": 0.5555405616760254, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/bd6b418cac4be5aa191aa0595f24f2e8fe9002e29ce4e78147834db7ff702c5d.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "bd7c66a236da95a846591b44bcd70ea87e0ed5729756bb4dee9df5a7a71e06b9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "871bafc0bf1e7fae889d088104566404a870126ef0e06b33b8299b7fd7fddfc0", "generation_seconds_batch": 19.782794303027913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8133578300476074, "target_z": 1.1406249193911457, "ce": 6.24500846862793, "genuineness": 3.9801597595214844, "identity": 0.4143817126750946, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/bd7c66a236da95a846591b44bcd70ea87e0ed5729756bb4dee9df5a7a71e06b9.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "be2e4948c0d288409d458d9405fdbb5d57003df628fb806c391aaf1906551de8", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6b1a0e83587af8532bac8b43067ac46fb83f9775ad875dbfd947302eeffbd54f", "generation_seconds_batch": 13.878058997099288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5432472825050354, "target_z": 0.6210937020825144, "ce": 6.205295085906982, "genuineness": 4.432034492492676, "identity": 0.6673455238342285, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/be2e4948c0d288409d458d9405fdbb5d57003df628fb806c391aaf1906551de8.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": "be5c768e6e9637947dc01fd5c2a21f1ee7b295ade19ff08d34dd7371a638ca6c", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee101ff84baed73125a461d15e7ce9928f6bb2350b3b2f4ee9976ee05689116b", "generation_seconds_batch": 14.752807327080518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6407307982444763, "target_z": 0.8085937092477459, "ce": 6.078212261199951, "genuineness": 3.8546390533447266, "identity": 0.6125365495681763, "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_Pride/be5c768e6e9637947dc01fd5c2a21f1ee7b295ade19ff08d34dd7371a638ca6c.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "beebcaf8ef8cb4af0cdefc95c6540f7bf916128062021a24ac56520cb28f89ae", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0e636a7f44286b995100e026852d6562a5d3df0078de15b88de26dffd1221b81", "generation_seconds_batch": 18.659525066032074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1464265584945679, "target_z": 1.7812500394087734, "ce": 5.919358730316162, "genuineness": 4.005263805389404, "identity": 0.3659924268722534, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/beebcaf8ef8cb4af0cdefc95c6540f7bf916128062021a24ac56520cb28f89ae.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "bf7ca7578aaa4f4791dd298816780f1c9d3ada7f62280da6a8d4bc669da41702", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3842c0b59910eef89f83be37652d8b148039cc005e90b61031d19e620ffea627", "generation_seconds_batch": 14.086009127902798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0936230421066284, "target_z": 1.6796876406176682, "ce": 5.903473377227783, "genuineness": 3.9425034523010254, "identity": 0.46972009539604187, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/bf7ca7578aaa4f4791dd298816780f1c9d3ada7f62280da6a8d4bc669da41702.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "bfe51f7d31b595b7be0e7d36e4ce639c07dc897a49cb2e401121c8a1268c7ca4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "46efce7cb8f8a8c61901d740b36a36daf198e83ed4b955ccca874e1e6c197cee", "generation_seconds_batch": 21.697387842927128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0895612239837646, "target_z": 1.671875130765475, "ce": 5.927301406860352, "genuineness": 3.9425034523010254, "identity": 0.7520667910575867, "hypothesis": "De deur 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_Pride/bfe51f7d31b595b7be0e7d36e4ce639c07dc897a49cb2e401121c8a1268c7ca4.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "c024c14722a415c3c3072cf5600b55258b5eb3648229111c4d320ab242b0d4ca", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9f39ce3a0419a766fe7dcc8762f0fbd852e6bb8a36a717e7dee0382467aeebc2", "generation_seconds_batch": 18.463542485958897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.109870195388794, "target_z": 1.7109374507390334, "ce": 5.895530700683594, "genuineness": 4.017816066741943, "identity": 0.5390253663063049, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c024c14722a415c3c3072cf5600b55258b5eb3648229111c4d320ab242b0d4ca.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "c06dc6bc471da785be474d0f822cdfa2fd9034065276b3cda7acbb1732ea8402", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4ac361da6498ba1fe338dfe082ea8f81f7140a430579b892d815dc46a8aedcf2", "generation_seconds_batch": 20.149408608092926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8336669206619263, "target_z": 1.1796874686521122, "ce": 6.173524379730225, "genuineness": 3.848362922668457, "identity": 0.15751107037067413, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c06dc6bc471da785be474d0f822cdfa2fd9034065276b3cda7acbb1732ea8402.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "c0a7625ced869097d10075e51ed455f28b2661fc9dafec026e9e9ad8639320d8", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4e3c51e9e0dac17d7e3af5246ddd45c9375e7180fca0f56fc9e4ff2e289c0008", "generation_seconds_batch": 18.56874211190734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9798921942710876, "target_z": 1.4609374793999594, "ce": 6.038498878479004, "genuineness": 4.243753433227539, "identity": 0.47998523712158203, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay después.", "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_Pride/c0a7625ced869097d10075e51ed455f28b2661fc9dafec026e9e9ad8639320d8.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": "c0bced7dfae548d3c857cfc265753210ff12af9f49c2c4b24ec048dff687fdd4", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "40339fd078d463047c32240e9b94aadc98346d3ce2313a79811ee9a92a844d0f", "generation_seconds_batch": 21.844082860974595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.096890687942505, "target_z": 3.6093748226605205, "ce": 6.09409761428833, "genuineness": 4.218649387359619, "identity": 0.5862091779708862, "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_Pride/c0bced7dfae548d3c857cfc265753210ff12af9f49c2c4b24ec048dff687fdd4.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "c12e5ad92322cad4b317acc4b6036a690112af18d6f8bc181d47a71ee98452b9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e3fe32fb4add3ea119b34246e59625b39cd74da7bdd9960c08a3e096ffbe676b", "generation_seconds_batch": 16.975801111897454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0164484977722168, "target_z": 1.5312499534259953, "ce": 6.221180438995361, "genuineness": 4.356721878051758, "identity": 0.6490925550460815, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c12e5ad92322cad4b317acc4b6036a690112af18d6f8bc181d47a71ee98452b9.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "c143a0cc6149f49d4bd3c502f4eda4fa72f2555c17d7f0a4cbf16808d6e08c67", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "23a1f8c801472970d55bdbe3345d440e567a056129099cf9f5f1bc3d3c1944f8", "generation_seconds_batch": 18.774364633951336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4713716506958008, "target_z": 2.4062501397220144, "ce": 6.205295085906982, "genuineness": 3.8671910762786865, "identity": 0.6006263494491577, "hypothesis": "De deur 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_Pride/c143a0cc6149f49d4bd3c502f4eda4fa72f2555c17d7f0a4cbf16808d6e08c67.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "c15c89873c2f34d1f9c3698eafafc70f9d6c075deb115a964a0887d166b7ff10", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "55c499a550e65e5f712a406e9add90a39e9e0d7215671fda12a65749a7bb0399", "generation_seconds_batch": 18.425076197017916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3413935899734497, "target_z": 2.156250053739236, "ce": 6.109982967376709, "genuineness": 3.9299514293670654, "identity": 0.21266372501850128, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c15c89873c2f34d1f9c3698eafafc70f9d6c075deb115a964a0887d166b7ff10.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "c1c2fa19f65903c11ed242f2e9cd815749862bbfb49337959c06238eed301526", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ae93a3527ff73e7d8a2aeb219cdcc5a4939c4756e3ad40e7da0e5cc4229f1fe4", "generation_seconds_batch": 19.3764107770985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43560928106307983, "target_z": 0.41406253493050355, "ce": 6.197352409362793, "genuineness": 4.720732688903809, "identity": 0.6149575710296631, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c1c2fa19f65903c11ed242f2e9cd815749862bbfb49337959c06238eed301526.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "c1cb9b2eea1dbb4f405fdf35cebdcc800c047daf525a093a7b85f3c6a947e54b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1feb87d15fa9732b2878dcc892d90932cf9751e13ea7a3f37eb8374685007d07", "generation_seconds_batch": 19.618525799014606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8174196481704712, "target_z": 1.148437429243339, "ce": 6.149696350097656, "genuineness": 4.231201171875, "identity": 0.6035066246986389, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c1cb9b2eea1dbb4f405fdf35cebdcc800c047daf525a093a7b85f3c6a947e54b.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "c3488fb9e6495dd1ad4c0ee21dc7d6d1d884e3d9b19c9deb08a9117ec2031965", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6a7b23e1044058b332e6a68583bb913b1462d495cda2bf74bc673749a95690c6", "generation_seconds_batch": 22.189591214992106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5188764333724976, "target_z": 0.5742187576130585, "ce": 5.919358730316162, "genuineness": 3.9801597595214844, "identity": 0.7517673969268799, "hypothesis": "La porte 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_Pride/c3488fb9e6495dd1ad4c0ee21dc7d6d1d884e3d9b19c9deb08a9117ec2031965.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "f4cc85077556a1e0b7296d32725c93175c637e0c721f70456ff8cc1e9dd8cb89", "generation_seconds_batch": 13.691055019036867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3025848865509033, "target_z": 0.1582031238804326, "ce": 6.0146708488464355, "genuineness": 4.545003414154053, "identity": 0.6359388828277588, "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_Pride/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "c3a2afed5e87b19112ba74a7e7e9470f19c9d1cb6e48bc272e06d2be202ecc4d", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d0b19a5dd715b556a4a66eea0c9a8f079686d3c515a54a03fd00560e52dde996", "generation_seconds_batch": 15.267406283062883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.589958131313324, "target_z": 0.7109374507390335, "ce": 6.062326908111572, "genuineness": 4.093128204345703, "identity": 0.7123266458511353, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c3a2afed5e87b19112ba74a7e7e9470f19c9d1cb6e48bc272e06d2be202ecc4d.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "c3a57f77efd9a3178f2475302c1413f44c9d971738061644c7a1712b8a7dedd0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "cd0722bd9dc742ead42b08833aa715e6080882a9aa8d4c28c590032e65bc9839", "generation_seconds_batch": 13.86695584107656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8133578300476074, "target_z": 1.1406249193911457, "ce": 6.1894097328186035, "genuineness": 4.068024158477783, "identity": 0.675683856010437, "hypothesis": "J'ai trouvé la 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_Pride/c3a57f77efd9a3178f2475302c1413f44c9d971738061644c7a1712b8a7dedd0.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "c3acd42bb3a7ce4454077c5b1fa7280a95b7b60b6ec658379593dab5bec05e77", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "a37728c39c2de093c1014f5bf8599eafef203e29cab1723fa2a2aafb58d8af40", "generation_seconds_batch": 18.577165237045847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.267486810684204, "target_z": 3.9374997778778233, "ce": 6.395919322967529, "genuineness": 4.143336772918701, "identity": 0.43076062202453613, "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_Pride/c3acd42bb3a7ce4454077c5b1fa7280a95b7b60b6ec658379593dab5bec05e77.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "c3bc7c9f0d6ac72bd73347fc4dd0096e0c1526115a9777d5b2f78efe4adb81ca", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "451104c6d5c07380fbdc1a89d1cd35e784e7fba17440105435b2255927d7d0c4", "generation_seconds_batch": 23.00570641295053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1943743228912354, "target_z": 3.7968750591131597, "ce": 6.395919322967529, "genuineness": 4.055472373962402, "identity": 0.4487498998641968, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c3bc7c9f0d6ac72bd73347fc4dd0096e0c1526115a9777d5b2f78efe4adb81ca.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "c3cf71c7cae65b379953663d8a05218e225efe650ce94df9ef503a20e8edfd0d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1d8b11cd00b8a406f8bc7e8db9a6985f8a829a82f84bce38d5b887460b8d7cd7", "generation_seconds_batch": 16.914572459994815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.048943042755127, "target_z": 1.5937500322435418, "ce": 5.816103935241699, "genuineness": 3.873466968536377, "identity": 0.5512280464172363, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c3cf71c7cae65b379953663d8a05218e225efe650ce94df9ef503a20e8edfd0d.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "c3e1d81f1f3acc985c1f1a32ba0a08d2914cbffe3e9f64677e2db4b8cf9da52f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "433795243e09032f5052d9c087c030214815f0135a48d33e42231414ba58bf0f", "generation_seconds_batch": 20.869212412973866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5554327368736267, "target_z": 0.6445312316390943, "ce": 6.403861999511719, "genuineness": 4.319066047668457, "identity": 0.19980567693710327, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c3e1d81f1f3acc985c1f1a32ba0a08d2914cbffe3e9f64677e2db4b8cf9da52f.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "c3e8fdfb37e8f0a5ef64910403cec59d1c8d60608e0af82722b71f77bfad2f4d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7a8b096be6c04679697ab549a4a663f932abb6a61167d49460497aa8e50049cc", "generation_seconds_batch": 19.51467111497186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5168455243110657, "target_z": 0.5703125026869618, "ce": 6.054384231567383, "genuineness": 3.8922953605651855, "identity": 0.5195890069007874, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c3e8fdfb37e8f0a5ef64910403cec59d1c8d60608e0af82722b71f77bfad2f4d.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "c42e3c9670fa63e174a38b5c835d7fe8b6c7d38d53e7efaa6aa37e37441f877a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "89730a19d27928d281808591cde7d2dfb1339cd168c93e57910444aa3ca3f3d1", "generation_seconds_batch": 13.821916791028343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8092960715293884, "target_z": 1.1328125241826563, "ce": 6.205295085906982, "genuineness": 4.381826400756836, "identity": 0.49498969316482544, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c42e3c9670fa63e174a38b5c835d7fe8b6c7d38d53e7efaa6aa37e37441f877a.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "c8d5a163ea991e05de7231ce999a02328d946e753bca1d9b5082d50a93d1f673", "generation_seconds_batch": 16.683026059996337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32492485642433167, "target_z": 0.2011718707456438, "ce": 6.213237762451172, "genuineness": 4.2249250411987305, "identity": 0.7089860439300537, "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_Pride/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "c546c3baccf8ab69d1be5a7ac8e8b85a914e287433ef86cbe681c900e8664e90", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04f85cdfb217fd95731cfada10e6b881f8b05a4469353059cd377e796d7cf09e", "generation_seconds_batch": 17.35515656589996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5046600699424744, "target_z": 0.5468749731303819, "ce": 6.300607204437256, "genuineness": 4.519899368286133, "identity": 0.5506463050842285, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c546c3baccf8ab69d1be5a7ac8e8b85a914e287433ef86cbe681c900e8664e90.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "c55ba2a654277ddec12da2604bf9098a69eda54a5c2852b29ee32b16ac0688b4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "93a293947ab171cc1d4e9379c175938ea131f283890e7634c6bb201b9dfb387d", "generation_seconds_batch": 18.64211778191384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2682809829711914, "target_z": 2.015625105687165, "ce": 6.046441555023193, "genuineness": 4.017816066741943, "identity": 0.5037057399749756, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c55ba2a654277ddec12da2604bf9098a69eda54a5c2852b29ee32b16ac0688b4.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": "c5dd19800b0fa1a73dd804e6fa6f08d2f4b4c1e5301778dbf5acf26879d5845d", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "99bd857b6920828d234885b9f443e4b433f9619cb21796e17faa054649a17a48", "generation_seconds_batch": 13.914176505990326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0042630434036255, "target_z": 1.5078124238694153, "ce": 6.221180438995361, "genuineness": 4.419482707977295, "identity": 0.5432591438293457, "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_Pride/c5dd19800b0fa1a73dd804e6fa6f08d2f4b4c1e5301778dbf5acf26879d5845d.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "c61557aadd929155ac9ec02f7e93384331d8f1f457a3f8837184ff12c82395ef", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7df993c400b6c4f39ba92dde04460b24a5f009310425aea0867e68085bfeaf03", "generation_seconds_batch": 15.173866345081478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1342411041259766, "target_z": 1.7578125098521933, "ce": 6.054384231567383, "genuineness": 3.7918784618377686, "identity": 0.28304463624954224, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c61557aadd929155ac9ec02f7e93384331d8f1f457a3f8837184ff12c82395ef.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "c7394bf6a938758ffd43beb2fd2b265d809c0723f13249fd7901148e14fc5bee", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e1b7a66b3bd9ff28fcec72506168fdaddeb7e94359066e9aaef192c0409af9e4", "generation_seconds_batch": 19.257681305985898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4589647054672241, "target_z": 0.4589844092587631, "ce": 6.24500846862793, "genuineness": 4.13078498840332, "identity": 0.49914324283599854, "hypothesis": "Ik heb het klein 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_Pride/c7394bf6a938758ffd43beb2fd2b265d809c0723f13249fd7901148e14fc5bee.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "c740de11f885762465ad723efb8364c7e6b09fefc64e5e60f56eec07ef649e51", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1323da089e687aa8aab3f071968a701fac3d1e67cc9752326917448894822ea", "generation_seconds_batch": 19.602618237026036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6651017069816589, "target_z": 0.8554687683609057, "ce": 6.1020402908325195, "genuineness": 4.494794845581055, "identity": 0.6433530449867249, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c740de11f885762465ad723efb8364c7e6b09fefc64e5e60f56eec07ef649e51.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "247c5235020eaafecc31fb17ccbf1354398b7d16d81e46ce063c49e56c0f7ca1", "generation_seconds_batch": 14.535842639044859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.375697523355484, "target_z": 0.2988281292543562, "ce": 6.205295085906982, "genuineness": 4.325342178344727, "identity": 0.6669014692306519, "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_Pride/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d", "bucket": "emo_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "ab2f093bd4ea560c15cfb539ed7ea8d31eaaec24ffbcca592f54416ce18c602b", "generation_seconds_batch": 14.14030745497439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2888762652873993, "target_z": 0.13183593179020614, "ce": 6.467403411865234, "genuineness": 4.068024158477783, "identity": 0.2653585970401764, "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_Pride/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "c8ba7fd0aa96d6deda836733cde9c525f5963514c32dddde8713cb4e6ea94ec3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3b3b8b57b7b1d0827de7677636663dbc838bee1f1786823cac6fa9bbe2ba99d6", "generation_seconds_batch": 20.59252494201064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7321215867996216, "target_z": 0.9843749516346874, "ce": 6.221180438995361, "genuineness": 4.394378662109375, "identity": 0.826793909072876, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c8ba7fd0aa96d6deda836733cde9c525f5963514c32dddde8713cb4e6ea94ec3.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "c92534558c0bd68fa0ad99cd12c5f12bee8dd2cc6e7c4ad8d0c5bded53a8223c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "10ee6927db798fbe2e8d10bbb26b379f01be2a3f2591c529dad3e0163e5b080d", "generation_seconds_batch": 20.149408608092926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0083248615264893, "target_z": 1.5156249337216086, "ce": 6.260893821716309, "genuineness": 3.823258876800537, "identity": 0.26022887229919434, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c92534558c0bd68fa0ad99cd12c5f12bee8dd2cc6e7c4ad8d0c5bded53a8223c.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "c96ae5e7b1ac7d06b5528466183b3bfbbef35ae78685b4d4eeedc9e4d21956b1", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5aec5d8b16f6908344f2fb16f9032cc7f581dd54b90831a0bc0bffa22bac8a66", "generation_seconds_batch": 19.941161594935693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6793180704116821, "target_z": 0.8828125528435823, "ce": 6.340320587158203, "genuineness": 4.18726921081543, "identity": 0.270393967628479, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c96ae5e7b1ac7d06b5528466183b3bfbbef35ae78685b4d4eeedc9e4d21956b1.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": "c9e976e008f33b1311a5783d598768ad91f523723518d74e843160692dfc450e", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4770098f03849e070b88cc96b9099e241b28767d1bf851dca50cfdf30335cf1e", "generation_seconds_batch": 22.57565895805601, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5371546149253845, "target_z": 0.6093750519479284, "ce": 6.038498878479004, "genuineness": 4.099404335021973, "identity": 0.750670313835144, "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_Pride/c9e976e008f33b1311a5783d598768ad91f523723518d74e843160692dfc450e.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "c9f0c286ad373f3a4f6d7c52c614f2273513e447a09e47145e27d63dd4bde44e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "aff544106384b754bc00d87d6ae5c9abb6e7f3875b033995a8d735c4a9f699c2", "generation_seconds_batch": 21.245069639990106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.606205403804779, "target_z": 0.7421874901478067, "ce": 6.252951145172119, "genuineness": 4.068024158477783, "identity": 0.7334593534469604, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/c9f0c286ad373f3a4f6d7c52c614f2273513e447a09e47145e27d63dd4bde44e.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "ca48d7979e30fe47def83809437c0e06d99ec93723096bab6c81df3fa894722e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "65d3bec0536dc44781e51374885b7d4afb8d70eb0ef0bbdf1d37c93705d314d7", "generation_seconds_batch": 18.557461034040898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1545501947402954, "target_z": 1.79687505911316, "ce": 6.23706579208374, "genuineness": 3.7918784618377686, "identity": 0.26256176829338074, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ca48d7979e30fe47def83809437c0e06d99ec93723096bab6c81df3fa894722e.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "ca492462fc9a784d887d547926a36cb927ec98017a2e2ff9b6a543d05c58eca1", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "55c312aaa67355d595449ea544bb3f4890e188ec1eb57f52ea2e7215701ea03b", "generation_seconds_batch": 22.80045954999514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7232040166854858, "target_z": 2.8906250626957757, "ce": 6.054384231567383, "genuineness": 3.948779582977295, "identity": 0.38827913999557495, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ca492462fc9a784d887d547926a36cb927ec98017a2e2ff9b6a543d05c58eca1.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "cacbaf2895fbc65f338cbe0f75d6f2204a106f5ee88ef919128eccbc5db11421", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4b8a61bcd28f6a266d2e6c407d42a0a95665194f8e3b4cac60032d53141154aa", "generation_seconds_batch": 16.29050032107625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1707974672317505, "target_z": 1.828125098521933, "ce": 6.268836498260498, "genuineness": 3.7918784618377686, "identity": 0.17442560195922852, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cacbaf2895fbc65f338cbe0f75d6f2204a106f5ee88ef919128eccbc5db11421.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "cae81acd940bf2432332817816e3e77028ad2134f95ceab80b28c6433d1e1105", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7b6c55d9d1418c80831952b425b4a9bb0539e464724453c0057974c01d79932b", "generation_seconds_batch": 18.58358512900304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.760554313659668, "target_z": 1.0390625206000406, "ce": 6.0146708488464355, "genuineness": 4.2751336097717285, "identity": 0.673973798751831, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cae81acd940bf2432332817816e3e77028ad2134f95ceab80b28c6433d1e1105.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "cb550f5c14ffa1ae1febbec671668672996a5617d51df7d70162243b51e0be0f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7924b3eed252f88e9b6476c01b64f57f45dcf1b833dd6d68c81cbad7c0e48dc9", "generation_seconds_batch": 14.424764416995458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7881929874420166, "target_z": 3.0156249910434605, "ce": 5.935244083404541, "genuineness": 3.9927117824554443, "identity": 0.5978768467903137, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cb550f5c14ffa1ae1febbec671668672996a5617d51df7d70162243b51e0be0f.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "cbb4c0a6a3480345c7da7387e3c98eaef7b9506650ad946317c610c910b54454", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7eda6206418d42a49b92ec9f61d1933cfe4e85b2efde734c4ba8be7688a3ce2c", "generation_seconds_batch": 19.782794303027913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2560955286026, "target_z": 1.9921875761305847, "ce": 6.157639026641846, "genuineness": 3.8546390533447266, "identity": 0.19407519698143005, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cbb4c0a6a3480345c7da7387e3c98eaef7b9506650ad946317c610c910b54454.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "cbccf7541e91302c4b546f90e9199a926ae771b6f70a83a87a6412612b6afe33", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "981ec6d6cc0beeb03baaab0920e378850566c0ee0c8eebb9c17213f5a36f662b", "generation_seconds_batch": 15.003483689040877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47419649362564087, "target_z": 0.48828126388263604, "ce": 6.213237762451172, "genuineness": 4.344170093536377, "identity": 0.8234105110168457, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cbccf7541e91302c4b546f90e9199a926ae771b6f70a83a87a6412612b6afe33.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": "cbd72fc8dbe41e9b707ce3c88db877c8b35645884a83dcf5604d924793530fbe", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4cb8639163b4f4e6f426ac0c949b3a6c52607a6832dc433abf83849d6a1115ed", "generation_seconds_batch": 14.8054414720973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.91737699508667, "target_z": 5.187499978504306, "ce": 6.117925643920898, "genuineness": 4.193545341491699, "identity": 0.5355226993560791, "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_Pride/cbd72fc8dbe41e9b707ce3c88db877c8b35645884a83dcf5604d924793530fbe.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "cc04dbfae7619f93e04f31f30840b0deb30d05fc008a346e08a23ce0a83d807f", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ec6db015445abeb7d2b4eb65cc8dd88927be5f2c2d69e48f9d3c7d7a4245a29e", "generation_seconds_batch": 17.35515656589996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4802892208099365, "target_z": 0.500000028660926, "ce": 6.1894097328186035, "genuineness": 4.457139015197754, "identity": 0.6696491837501526, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cc04dbfae7619f93e04f31f30840b0deb30d05fc008a346e08a23ce0a83d807f.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "cc561965453b79ade50d31691229a396303c44ef3ad96bbcc411141325d143fd", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "f8111cb904209d32ce06791692778e7eee6b53941ed508f31fb58a38129086e5", "generation_seconds_batch": 19.118351590936072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1212615966796875, "target_z": 3.65624988177368, "ce": 5.879645347595215, "genuineness": 4.017816066741943, "identity": 0.21819952130317688, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereitst.", "wer": 0.10526315789473684, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cc561965453b79ade50d31691229a396303c44ef3ad96bbcc411141325d143fd.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": "cca8dfb7c07e274a9dd323716901481c33eb78aec73cd3ebe4fea19c9adc1d6e", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b2a3c13e61eb1e10e0995d206c80421447532e45548edd9d42adaa5dbb61ed29", "generation_seconds_batch": 13.811579633969814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0326957702636719, "target_z": 1.5624999928347685, "ce": 6.252951145172119, "genuineness": 4.15588903427124, "identity": 0.7092565298080444, "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_Pride/cca8dfb7c07e274a9dd323716901481c33eb78aec73cd3ebe4fea19c9adc1d6e.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "ccab0272fab52f416a26e2809ea68cf81814edf5584d4aa78dd013317e76c875", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e22481d2c29a5d058c56de6da98428d4f52b51fc48da457acb778c5a3772d2cd", "generation_seconds_batch": 22.257037751958705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.624483585357666, "target_z": 0.7773437844826766, "ce": 6.221180438995361, "genuineness": 4.030367851257324, "identity": 0.6645950675010681, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ccab0272fab52f416a26e2809ea68cf81814edf5584d4aa78dd013317e76c875.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "ccd47d3c0b3b71c7dc307c0e90d45cf3ad1c49c7446be54c34a53ca5ffc3d68e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b8c8ccfd41d04a05d4986ac3365b6f637e1b9a989292b12cb7e445c285ce5fdd", "generation_seconds_batch": 18.58358512900304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.646823525428772, "target_z": 0.8203124740260358, "ce": 6.292664527893066, "genuineness": 4.243753433227539, "identity": 0.614076554775238, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ccd47d3c0b3b71c7dc307c0e90d45cf3ad1c49c7446be54c34a53ca5ffc3d68e.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "cd38759432170f63e183c65253a6bca581b40e8e4652846300b4a492101f20c8", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6fa06ebeeb0e3af09f91b65143796641a881f3ba60b5fe946a955d47616842d9", "generation_seconds_batch": 19.663066647946835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8133578300476074, "target_z": 1.1406249193911457, "ce": 6.141753673553467, "genuineness": 4.105680465698242, "identity": 0.6862800121307373, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cd38759432170f63e183c65253a6bca581b40e8e4652846300b4a492101f20c8.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "cd4bd1740ab2b3ad900ede6cf8c1cee670491f301bc6bf2c7682278f5aae82ac", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6145c331b577220467dd1cfb3e790f564a71e462efbf1fe41f472f4a00aa115a", "generation_seconds_batch": 18.593736000941135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.414506196975708, "target_z": 2.296875001791308, "ce": 6.1894097328186035, "genuineness": 4.218649387359619, "identity": 0.6831737160682678, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle connaît.", "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_Pride/cd4bd1740ab2b3ad900ede6cf8c1cee670491f301bc6bf2c7682278f5aae82ac.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "cd6b92bf5e66f2c40e7658c458a6dc6b07cd841201d467ffd71496c11c7ef21d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4aa8b3ea3cc63e7c1ebaa3f47dcb4e5660e106ea88d43ba53a3d22b60daf3289", "generation_seconds_batch": 18.514910822967067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0643961429595947, "target_z": 3.5468747438429737, "ce": 6.109982967376709, "genuineness": 3.9550557136535645, "identity": 0.3568308353424072, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cd6b92bf5e66f2c40e7658c458a6dc6b07cd841201d467ffd71496c11c7ef21d.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "cdb7c16cb30fb2acee2c2ff631a31daa8197ffe57c343ac8987da1e2b43dd4a9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e9d82daf936ce3ad6a7628cc0ea7da22cf15824e83b0f57f1fd0f9178c193aad", "generation_seconds_batch": 20.563671389012598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2479718923568726, "target_z": 1.9765625564261982, "ce": 6.165581703186035, "genuineness": 3.6789097785949707, "identity": 0.21026521921157837, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cdb7c16cb30fb2acee2c2ff631a31daa8197ffe57c343ac8987da1e2b43dd4a9.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "ce1c5495c0d4b0835532fed3f941f67464c2dbc7420687dbbb1689a8a2806fd8", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b3e2c757de5f37106d9a4657433d197bd105e84681527db09783969423384642", "generation_seconds_batch": 14.168399067013524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8255432844161987, "target_z": 1.1640624489477256, "ce": 6.141753673553467, "genuineness": 4.13078498840332, "identity": 0.722811222076416, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ce1c5495c0d4b0835532fed3f941f67464c2dbc7420687dbbb1689a8a2806fd8.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": "ce4ef3bf656e9da9f275a70556d6776de2b6c6d283aaef52d241de4c2b237a01", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "471d1d3507fa12a60a66cdc465f1804cd4d07d453c73119af59371f2d9689602", "generation_seconds_batch": 19.631051381933503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.317022681236267, "target_z": 2.1093749946260765, "ce": 6.252951145172119, "genuineness": 4.124508857727051, "identity": 0.6267178654670715, "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_Pride/ce4ef3bf656e9da9f275a70556d6776de2b6c6d283aaef52d241de4c2b237a01.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "4f7969ea8c4c71105da424dc87d59bc8474451c7cb5e694a8ac5498278039ed0", "generation_seconds_batch": 13.725433557992801, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5391855239868164, "target_z": 0.613281306874025, "ce": 6.419747352600098, "genuineness": 4.256305694580078, "identity": 0.49058324098587036, "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_Pride/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "cf7a60e22e47489655b84445c43e6a97585a96ebfbb5b37cf3fef1d9d867cd20", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bc38657893e852ac17b038d012c410b032e9507a664c71c1fa5f725c2c100a65", "generation_seconds_batch": 22.745843692915514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0083248615264893, "target_z": 1.5156249337216086, "ce": 6.268836498260498, "genuineness": 4.231201171875, "identity": 0.6988662481307983, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cf7a60e22e47489655b84445c43e6a97585a96ebfbb5b37cf3fef1d9d867cd20.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "cf9e674d794e47063bc537e12e61269b0f05b50beb57b2ae9d29df8ed4d8e948", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "df059c73cc68bc9b8842b999605c42d30db2c1151eae4a22e1b3444ef8aa7c08", "generation_seconds_batch": 19.471119842026383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.685410737991333, "target_z": 0.8945312029781682, "ce": 6.316492557525635, "genuineness": 4.21237325668335, "identity": 0.3701908588409424, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cf9e674d794e47063bc537e12e61269b0f05b50beb57b2ae9d29df8ed4d8e948.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "cfc6b12a31c0c0963ed703a5b9431d34509ed846545ccebd9f218430433e1cd7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3e97626812239591bf97cf7b5d23a9ee28c6a0db3675e103fb29c05595ad219d", "generation_seconds_batch": 20.033051440957934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3495172262191772, "target_z": 2.1718750734436227, "ce": 6.221180438995361, "genuineness": 3.8671910762786865, "identity": 0.30020871758461, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cfc6b12a31c0c0963ed703a5b9431d34509ed846545ccebd9f218430433e1cd7.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "cfe9797b9b8ed2ab37dcc71d7340d80faff4aed90ea552e1bff37b1a73b92496", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "88a2ea907307513ab8884373931582d923aec9c555f7f385d05207c3ebef2eac", "generation_seconds_batch": 19.783498172997497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6574208736419678, "target_z": 4.687499806538749, "ce": 5.895530700683594, "genuineness": 4.074300289154053, "identity": 0.48935839533805847, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "wer": 0.06666666666666667, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/cfe9797b9b8ed2ab37dcc71d7340d80faff4aed90ea552e1bff37b1a73b92496.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "d04eed935a201068e83d48a33144467c53943e12f19fa7e1145962196e1ab4e2", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "40565a29055ed58757a8cb40fb0750396d18e762e1c71882d4eb4c00bf1eb9b9", "generation_seconds_batch": 14.61174995393958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0773757696151733, "target_z": 1.6484376012088948, "ce": 6.1894097328186035, "genuineness": 4.055472373962402, "identity": 0.3794364929199219, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos.", "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_Pride/d04eed935a201068e83d48a33144467c53943e12f19fa7e1145962196e1ab4e2.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": "d0cf00e9aa279d022019629192623e5d12b51bdf3499d44aa884e90588cf6982", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Your message arrived after I had left.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c03aa4b429bff3c6b1f8215da00b06baecd6c077ebf3587b483277abad88e784", "generation_seconds_batch": 18.47389057802502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7768015265464783, "target_z": 1.0703124453651098, "ce": 6.395919322967529, "genuineness": 3.9550557136535645, "identity": 0.3042389750480652, "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_Pride/d0cf00e9aa279d022019629192623e5d12b51bdf3499d44aa884e90588cf6982.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "87f1a615d9095df78de8c911a745fd97275f2afbe79a20a91e8ecf3867c9206c", "generation_seconds_batch": 16.352260833024047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.951459527015686, "target_z": 1.4062500250783103, "ce": 6.403861999511719, "genuineness": 4.13078498840332, "identity": 0.2911648154258728, "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_Pride/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "d14697616a7b813ea50b728679921e50ee0724e0e075a045561a08d3d34dd8f8", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2cdf5478fbc4dffce909b3105a7c2796f8a45f0528947ab5823c444214792753", "generation_seconds_batch": 21.173416113015264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6427617073059082, "target_z": 0.8124999641738425, "ce": 6.149696350097656, "genuineness": 4.017816066741943, "identity": 0.760252833366394, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d14697616a7b813ea50b728679921e50ee0724e0e075a045561a08d3d34dd8f8.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "d1efbf4173e84bcd2e1a13276cdd679437a01254e5068b6b220f4fb6f5d77af3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e6ced391e3c4b078c782d7a982e7771eabea339a83b7ece8a69048d983475baa", "generation_seconds_batch": 18.85738208401017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5777727365493774, "target_z": 0.6875000358261575, "ce": 5.792276382446289, "genuineness": 4.2249250411987305, "identity": 0.6200661659240723, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d1efbf4173e84bcd2e1a13276cdd679437a01254e5068b6b220f4fb6f5d77af3.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "d2044d7fcbacfe3e780698ae2b2c4c0e0982b1eaeab9fa73956a2ad9e14786ba", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e4bcea8edef652ec55d6ae0df3aaf15a6fad9fda59eea4d849bbda82bdd161f7", "generation_seconds_batch": 18.429389627999626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7150803804397583, "target_z": 2.875000042991389, "ce": 5.879645347595215, "genuineness": 4.080576419830322, "identity": 0.5639805793762207, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d2044d7fcbacfe3e780698ae2b2c4c0e0982b1eaeab9fa73956a2ad9e14786ba.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "15ee300f6b8e3cdacd1129a1c22a995a8b0dd75b4ccf85f36ca23d74b8582053", "generation_seconds_batch": 13.751605028985068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33254075050354004, "target_z": 0.21582029805758027, "ce": 6.332377910614014, "genuineness": 4.632867813110352, "identity": 0.5269404649734497, "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_Pride/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "d25bc55e108717977fc5acc57aafe3c2ede8c8d969b8d41e19d8196e98047808", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "96ded612ce9b8ada10da56df2d158abdb9895fe2ec0488014ba98a2c4461d5f2", "generation_seconds_batch": 20.525546623044647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4112383723258972, "target_z": 0.3671874758173437, "ce": 6.403861999511719, "genuineness": 4.394378662109375, "identity": 0.34524595737457275, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d25bc55e108717977fc5acc57aafe3c2ede8c8d969b8d41e19d8196e98047808.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "d25d8dbef73f9cfabf576b876bcfeb79de7e91a252885b3f95a1581d92cb0852", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0f0ba4cdf8d40e7b3c9882f1e07dd1e0899df43d6c59c02c433a930880c4089f", "generation_seconds_batch": 13.730438478058204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.081437587738037, "target_z": 1.6562501110610883, "ce": 6.0146708488464355, "genuineness": 3.823258876800537, "identity": 0.6202912330627441, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d25d8dbef73f9cfabf576b876bcfeb79de7e91a252885b3f95a1581d92cb0852.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "d27f7402f04bf8d588d35d64d390884a84479db5b04cde1faf98a2292ce2427e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "990198c7cc53c609d8d491ac8a44b02ee5c82eea4d0bb09b18336a4d5aa05b9f", "generation_seconds_batch": 19.66440230398439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7057198286056519, "target_z": 0.9335937522391349, "ce": 6.316492557525635, "genuineness": 4.143336772918701, "identity": 0.32502830028533936, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d27f7402f04bf8d588d35d64d390884a84479db5b04cde1faf98a2292ce2427e.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "d2b37d85018a219b7d3e698534c388e5c8ee139079389454b9b0cd88df772394", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d98d783579161d9cdd86a4ad33070b70d9a733d4506d98d8605c6ad1751ca47f", "generation_seconds_batch": 19.069936497020535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5371546149253845, "target_z": 0.6093750519479284, "ce": 5.847874641418457, "genuineness": 4.394378662109375, "identity": 0.49604764580726624, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d2b37d85018a219b7d3e698534c388e5c8ee139079389454b9b0cd88df772394.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "d2f12239324d02d1a096482c53edcc24cc6851fd90ee8b165a44c824644f229e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c0e3746a640584149cf7684db69fc5f5919ba9b05945264d7b027f841021047", "generation_seconds_batch": 19.080924805020913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7321215867996216, "target_z": 0.9843749516346874, "ce": 6.062326908111572, "genuineness": 4.256305694580078, "identity": 0.6184203624725342, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d2f12239324d02d1a096482c53edcc24cc6851fd90ee8b165a44c824644f229e.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "d2f8247082682cc0811c24cb6199ad9b3399c2f0e701c19ad00d638904fd96e0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b2eb3d1cbc28a3d2085609fb2b65810958330ff99c21d02c137a109ac2928954", "generation_seconds_batch": 18.594208437018096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.203291893005371, "target_z": 1.8906249480520716, "ce": 6.221180438995361, "genuineness": 4.080576419830322, "identity": 0.32488852739334106, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d2f8247082682cc0811c24cb6199ad9b3399c2f0e701c19ad00d638904fd96e0.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "d30bd2da82c3808eaf746e04365bdbdefb09f966fdb6459871e3612130a2e080", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3661bedc68c714efa815bc777617c220b970a4e12a5d5138a0246cd09e73a156", "generation_seconds_batch": 18.43778326897882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.096890687942505, "target_z": 3.6093748226605205, "ce": 6.308549880981445, "genuineness": 3.998987913131714, "identity": 0.4415769577026367, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d30bd2da82c3808eaf746e04365bdbdefb09f966fdb6459871e3612130a2e080.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": "d33efdb9be7b03deb78bb6d2062c23a033925a25ae97cb063e5b46fce10f1914", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f4af0a3139c5cf7b058d1d9c8ab7b45f42a0d9cf275b33b8f4406ee9d9a0f41e", "generation_seconds_batch": 16.512293178937398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6175968647003174, "target_z": 2.6875000358261576, "ce": 6.078212261199951, "genuineness": 3.7542223930358887, "identity": 0.34436655044555664, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d33efdb9be7b03deb78bb6d2062c23a033925a25ae97cb063e5b46fce10f1914.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "d3864bc022e106cf23f77a8e6dfbdd62aaae83956baddbe95acade65003e0986", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ed32948a31dfdf0f69b9c73fc31af64549a66e48cd9ebe30f3c740539a86c237", "generation_seconds_batch": 22.617768086027354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.771945834159851, "target_z": 2.9843751809220955, "ce": 6.467403411865234, "genuineness": 4.118232727050781, "identity": 0.6112635135650635, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d3864bc022e106cf23f77a8e6dfbdd62aaae83956baddbe95acade65003e0986.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "d3c27dc828d4699a7f737ec2c445a3e4094dc5a5c2401118002f2729dac35344", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b186d9215745433bf3a150d572e2170e9a0783dd1c5b31d81ab75adf6115f627", "generation_seconds_batch": 23.00570641295053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7800694704055786, "target_z": 3.000000200626482, "ce": 6.419747352600098, "genuineness": 4.331617832183838, "identity": 0.6501849889755249, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d3c27dc828d4699a7f737ec2c445a3e4094dc5a5c2401118002f2729dac35344.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "736e025e54aae8498843a9ddd254bdb6f78124435bc23bb90b4c80508371ae1c", "generation_seconds_batch": 16.252383232000284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.755698561668396, "target_z": 2.953125141513322, "ce": 6.221180438995361, "genuineness": 4.413206577301025, "identity": 0.5561563968658447, "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_Pride/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.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": "d44f31df5372f82d74c637e4d4cd614f60682e99cc312199a15d076783c24332", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d40d4af824fc6c2b9d6a6ac88070126ef7cf2383ac4dd8036b8a05b8399c1cd", "generation_seconds_batch": 19.367547966889106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.606205403804779, "target_z": 0.7421874901478067, "ce": 6.38797664642334, "genuineness": 3.9927117824554443, "identity": 0.546190083026886, "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_Pride/d44f31df5372f82d74c637e4d4cd614f60682e99cc312199a15d076783c24332.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "d464ab99fed9436aa07076f239a427e76eefcd2a626ee79df48d08c12ff1b606", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9d609e36c1b5e1b4588fa78c3d1956e8d34f0c280035e39456058a057206279e", "generation_seconds_batch": 19.422576512093656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7873988151550293, "target_z": 4.93749966323412, "ce": 6.395919322967529, "genuineness": 4.13078498840332, "identity": 0.3813689947128296, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d464ab99fed9436aa07076f239a427e76eefcd2a626ee79df48d08c12ff1b606.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "d480a2734a25def4b8b820575e869157bd7fdb79b49064ef830d2232c742c31a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d7869c1b494aeb6f9e35a5d9a19c8af5261cba31e81e87015d8945ac35661bde", "generation_seconds_batch": 19.816462000948377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9108413457870483, "target_z": 1.328124926556377, "ce": 6.125868320465088, "genuineness": 4.105680465698242, "identity": 0.5125221610069275, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d480a2734a25def4b8b820575e869157bd7fdb79b49064ef830d2232c742c31a.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "d48f14b76d7a552cf77add849d3d2dd5fb56bdad8bee4aace8f67c7b85261b49", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f0c95e5fc2a1b67e042e36cce8e964e26a0e6634eca65129d8b0238f2c0ab715", "generation_seconds_batch": 19.12431089603342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39803749322891235, "target_z": 0.34179687611956744, "ce": 6.300607204437256, "genuineness": 4.369274139404297, "identity": 0.6184330582618713, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen het er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d48f14b76d7a552cf77add849d3d2dd5fb56bdad8bee4aace8f67c7b85261b49.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "d4b6f1210c57229fc08c01618af852f7a11928436da190b72268ac9499c032d9", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "13beb2fd018d6fb2b27504ef5f8ba967ea7a514182d439d0daae8b24c20d5bfe", "generation_seconds_batch": 18.79686761298217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8198933601379395, "target_z": 4.999999742051666, "ce": 6.1020402908325195, "genuineness": 3.986435890197754, "identity": 0.3211013078689575, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hin.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d4b6f1210c57229fc08c01618af852f7a11928436da190b72268ac9499c032d9.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "d4e617d9a9ae6b101e1304af3e16093ad682ee2f5b1341e21614623ab096f828", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f6401f2f308a4b6f9f3e4b01679a613471cf4e6dd153aa32d906dab726a79b25", "generation_seconds_batch": 18.434210898936726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6082363128662109, "target_z": 0.7460937450739034, "ce": 6.324435234069824, "genuineness": 4.174716949462891, "identity": 0.40623974800109863, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d4e617d9a9ae6b101e1304af3e16093ad682ee2f5b1341e21614623ab096f828.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "d4f96719f7834010a5eb863eb3bcdc553932a5c5579fa0f9ee6b94c9a08588de", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "450ff0d1588557cfaf154a631dfc123dd50fa05db21a985379ba890e07463115", "generation_seconds_batch": 18.80922235304024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.292651891708374, "target_z": 2.0625001648003245, "ce": 6.1020402908325195, "genuineness": 3.7667744159698486, "identity": 0.32656747102737427, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d4f96719f7834010a5eb863eb3bcdc553932a5c5579fa0f9ee6b94c9a08588de.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "d5030d7687166377aca2b315b60bcd2164fcb0d1ca2acf40cd20668c8b33e2bf", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2c46abca7ac18d8b321a4697ebef0c42b3b90956044d1701a286ded91233c61e", "generation_seconds_batch": 23.486162966000848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6955652832984924, "target_z": 0.9140624776086516, "ce": 6.348263263702393, "genuineness": 4.268857479095459, "identity": 0.16498245298862457, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d5030d7687166377aca2b315b60bcd2164fcb0d1ca2acf40cd20668c8b33e2bf.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "d5b7dd1dc2e3e2056a313ec3aed742eedcdb9566f9d4a160981f68f15f9a3c48", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b80900be42c81db855a7a50f01a6d4e48bd11bb4da61f1fac007410ecb37fffd", "generation_seconds_batch": 23.360744339996018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6500914096832275, "target_z": 2.750000114643704, "ce": 6.109982967376709, "genuineness": 3.7416701316833496, "identity": 0.21388311684131622, "hypothesis": "The 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_Pride/d5b7dd1dc2e3e2056a313ec3aed742eedcdb9566f9d4a160981f68f15f9a3c48.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "d5fb2cb7709d0df687505441481e65b50e20b676315cc0b6c25c811105df904f", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9fe01869589dcc4fd097b71e27424dbe6292b71e0821a2ec9f5f32393e978758", "generation_seconds_batch": 17.629598545958288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3657644987106323, "target_z": 2.2031251128523963, "ce": 6.292664527893066, "genuineness": 3.998987913131714, "identity": 0.19299307465553284, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d5fb2cb7709d0df687505441481e65b50e20b676315cc0b6c25c811105df904f.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "d6a938aaf6da275eb8fc4fb67f05eb17d2c203b78c2631978d5b66dfc52cd8e0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cd2c421d9bb833f15ac0f6e9bafcbbd135905d3f93c4bf9dc3b61e2d5dd69960", "generation_seconds_batch": 19.185118341003545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7402452230453491, "target_z": 0.999999971339074, "ce": 5.736677646636963, "genuineness": 3.9676074981689453, "identity": 0.6473004221916199, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d6a938aaf6da275eb8fc4fb67f05eb17d2c203b78c2631978d5b66dfc52cd8e0.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "d6ea391ce8f9a13a1b3a8c997d1a504fd7b2b4e912c32e0b35ceaeb2f2d63a4e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c479dbb892e80c79b3fa93c8286ef40a7a2a41f917e1281844646ede99bed7e5", "generation_seconds_batch": 13.737886777962558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.109870195388794, "target_z": 1.7109374507390334, "ce": 6.2767791748046875, "genuineness": 4.381826400756836, "identity": 0.7328097820281982, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d6ea391ce8f9a13a1b3a8c997d1a504fd7b2b4e912c32e0b35ceaeb2f2d63a4e.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "d6ebd11ba5f56536ec14b06c1356d6c484bb6d36197f61bf938f3e161343e617", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b54f2bd1d8d11c465314977b9111ae8851488fb0590f425d93e7da606f22e004", "generation_seconds_batch": 21.409045887063257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7361834049224854, "target_z": 0.9921874614868806, "ce": 5.839932441711426, "genuineness": 4.13078498840332, "identity": 0.41480129957199097, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos.", "wer": 0.23529411764705882, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d6ebd11ba5f56536ec14b06c1356d6c484bb6d36197f61bf938f3e161343e617.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "d7c2950f93e3aca047ecbaf50160bc85068aa8312a3ec101d50953b6d4ca1171", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ffcef6c16006e8fa129fae033f854d12a152d2413ab09f9a1bc99588b96cbb80", "generation_seconds_batch": 19.438440328929573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5919890403747559, "target_z": 0.7148437056651301, "ce": 6.070269584655762, "genuineness": 4.432034492492676, "identity": 0.7456374168395996, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d7c2950f93e3aca047ecbaf50160bc85068aa8312a3ec101d50953b6d4ca1171.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "d7d7f684605e07796f2c8bd52693d22a01f81a16c4e3ebe7150d238aa22a4e0e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "05a2ba7993a3417ac1ee28c1344284263819058d813964a8bec40eb77a02f9c1", "generation_seconds_batch": 14.201262893970124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3738881349563599, "target_z": 2.218750132556783, "ce": 6.109982967376709, "genuineness": 4.111956596374512, "identity": 0.7216752767562866, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d7d7f684605e07796f2c8bd52693d22a01f81a16c4e3ebe7150d238aa22a4e0e.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "d7dac01eb90af8725bbfa1f39fa1476401c98763798876852d77bbf0c4ff7cfc", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d0b42f0d257d863d2fcff11eaccc07bb166e15f519c5e17abfc00847a560f277", "generation_seconds_batch": 21.866524509969167, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8198933601379395, "target_z": 4.999999742051666, "ce": 6.221180438995361, "genuineness": 3.8671910762786865, "identity": 0.633037269115448, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d7dac01eb90af8725bbfa1f39fa1476401c98763798876852d77bbf0c4ff7cfc.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "d81599c80fb3dfd81095a06f15557386f857c1caf3378c0221d40d8dbb25248f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1a99b420c0cf03a6ab9cccfeb77314604c0dd46ebbfdf548d841d2e76948965a", "generation_seconds_batch": 13.86695584107656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0164484977722168, "target_z": 1.5312499534259953, "ce": 6.205295085906982, "genuineness": 4.243753433227539, "identity": 0.7643582820892334, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d81599c80fb3dfd81095a06f15557386f857c1caf3378c0221d40d8dbb25248f.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "d8708ccb266d82e1eb39f35737792e25da4486aa6106ae2162e5f2a5d5c33010", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c571857267f91f85edc53ab98740c3b74fbc650f87a52aca503db2a47fa7c3b6", "generation_seconds_batch": 14.189467989956029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.738657236099243, "target_z": 4.843750003582616, "ce": 6.292664527893066, "genuineness": 4.18726921081543, "identity": 0.30151474475860596, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d8708ccb266d82e1eb39f35737792e25da4486aa6106ae2162e5f2a5d5c33010.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": "d91cc072f581fe311f1d94409061daf5ce5b80e87dcc5927a5405c9ea3d23c37", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "562b43b077928646e890f3462ec7852294b28089b79e8f467c2fe5499411658a", "generation_seconds_batch": 13.864651568001136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6549471616744995, "target_z": 0.8359374937304225, "ce": 6.403861999511719, "genuineness": 4.13078498840332, "identity": 0.5675493478775024, "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_Pride/d91cc072f581fe311f1d94409061daf5ce5b80e87dcc5927a5405c9ea3d23c37.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "d9325d77414ffe26e2ce0d95fc3f801e1364a5daa0a961a3ae41fc7f73e8b3fb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e948f58aec1e6f39cfed359bc1ad5b8f9666d33c174b3b6a2197c1b65e4fb2fa", "generation_seconds_batch": 22.032132284948602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7402452230453491, "target_z": 0.999999971339074, "ce": 6.221180438995361, "genuineness": 3.7542223930358887, "identity": 0.7633688449859619, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d9325d77414ffe26e2ce0d95fc3f801e1364a5daa0a961a3ae41fc7f73e8b3fb.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": "d9a79df56d15ed9242e749bcd1a06486d08032bd7b8594d6a25b951f8df1635f", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8737f17ed570f49973fd442686c1eb0187da444ac499b2b8168942bc22312d39", "generation_seconds_batch": 14.707318197004497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4802892208099365, "target_z": 0.500000028660926, "ce": 6.038498878479004, "genuineness": 4.042920112609863, "identity": 0.5900870561599731, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d9a79df56d15ed9242e749bcd1a06486d08032bd7b8594d6a25b951f8df1635f.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "d9a95756930a64c35ad6e7a450af5518183760891c62c63827eb0265ff3da0db", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a4262a9dd44d2f732ab496b26d689fb85e401b23e3c85c56f53cf27c372a4063", "generation_seconds_batch": 19.12431089603342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4965364336967468, "target_z": 0.5312499534259952, "ce": 6.292664527893066, "genuineness": 4.162164688110352, "identity": 0.7330352663993835, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d9a95756930a64c35ad6e7a450af5518183760891c62c63827eb0265ff3da0db.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "d9c0fa147425e3014053dbce8380d656259223ebdb10db8981d4d209c004213f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "594ccc7805a9014c89959a9c5025b85edb9e2afae83d699f35080d8d998a83e1", "generation_seconds_batch": 19.260617975960486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.129385232925415, "target_z": 3.6718749014780667, "ce": 6.356205940246582, "genuineness": 4.068024158477783, "identity": 0.6134029626846313, "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_Pride/d9c0fa147425e3014053dbce8380d656259223ebdb10db8981d4d209c004213f.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "d9eb959f9f750e0608912fed9c57a8a337d4f227b9d359afa6c11b6f36d1de5c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "48b0d1edc21a309f5335faad2515d581a22d9a61d8442f62a725d9c2c8e590f9", "generation_seconds_batch": 13.821916791028343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.878346860408783, "target_z": 1.2656249623825346, "ce": 6.284721851348877, "genuineness": 4.344170093536377, "identity": 0.3653178811073303, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/d9eb959f9f750e0608912fed9c57a8a337d4f227b9d359afa6c11b6f36d1de5c.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "da58cf0157007a5eedff5a81461fae4fa39608243a72328eb12bcbfe92f5785a", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f99478a5d103c97dc8ebc705988b0fcb549bb6e21a9cefb5153921cc8c1b8918", "generation_seconds_batch": 18.853901631082408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.955521285533905, "target_z": 1.4140624202867995, "ce": 6.165581703186035, "genuineness": 4.093128204345703, "identity": 0.5224868655204773, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/da58cf0157007a5eedff5a81461fae4fa39608243a72328eb12bcbfe92f5785a.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "da6dd3d5eebde0dd087ea12a46780f6dfd6a4dfbb30e60ee4ecf506c439b4f24", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "59d27a856672f6447033a10b4a327548c0a64a2d6a12422004575bdf333a83a2", "generation_seconds_batch": 14.12924280797597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0311076641082764, "target_z": 5.406249795790902, "ce": 6.173524379730225, "genuineness": 3.9550557136535645, "identity": 0.34168392419815063, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/da6dd3d5eebde0dd087ea12a46780f6dfd6a4dfbb30e60ee4ecf506c439b4f24.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "d596d0bdbf4d334a04d1527ebcf8d69eef4c1034fec34e6fc85052c77d941989", "generation_seconds_batch": 16.154242236050777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5635563731193542, "target_z": 0.6601562513434809, "ce": 6.340320587158203, "genuineness": 3.911123275756836, "identity": 0.31906503438949585, "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_Pride/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "db5a9f4d06115d7a74ff1a6ea79a1dcc06cecd82a28eaeedc3319a9df2021d2e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3d8a8cfc16dea11ce67c12b824222522fc3c40c42dd2978be8d31d0622dfa286", "generation_seconds_batch": 18.54594405600801, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1179938316345215, "target_z": 1.7265624704434201, "ce": 6.260893821716309, "genuineness": 4.086852550506592, "identity": 0.13407039642333984, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/db5a9f4d06115d7a74ff1a6ea79a1dcc06cecd82a28eaeedc3319a9df2021d2e.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": "dbb6b88dc1670a9a73c0a9d3672f24e509ec51358570e6c9cffc84cefce9d1e5", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c335470e8e6b27b0b2fe6ee3cd49b6952ec541bde9dbc200d3042f380058600d", "generation_seconds_batch": 14.510694858036004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5594945549964905, "target_z": 0.6523437414912876, "ce": 6.197352409362793, "genuineness": 4.168440818786621, "identity": 0.6703802347183228, "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_Pride/dbb6b88dc1670a9a73c0a9d3672f24e509ec51358570e6c9cffc84cefce9d1e5.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "dc0a9f2e8adb89fa087c01ecd474ac7721f5a369aa4846f3320969031e2a4996", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "18a90b4cd9490b6320ec977bc88aed10373bb23f1d89743895c2f39276e051a7", "generation_seconds_batch": 22.708041613106616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4388771057128906, "target_z": 2.3437500609044677, "ce": 6.1020402908325195, "genuineness": 3.7416701316833496, "identity": 0.4053683578968048, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/dc0a9f2e8adb89fa087c01ecd474ac7721f5a369aa4846f3320969031e2a4996.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "dd0b4b17ea98bcd48ff85dafac270ed6dfe5882699db88e0f4dfd60632f7f581", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1f0760aefe14e7ff7fd7a6e5c1548708db5f9b86be6789405f1e69734727f98f", "generation_seconds_batch": 16.420895869960077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0854994058609009, "target_z": 1.6640626209132816, "ce": 6.24500846862793, "genuineness": 4.18099308013916, "identity": 0.40714728832244873, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/dd0b4b17ea98bcd48ff85dafac270ed6dfe5882699db88e0f4dfd60632f7f581.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "dd1664c9f4c5846033c459a1579dbd797c764ac1179488cc427dc78ede99de37", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "6d2c0baf19aef1188f1a67d17d5f64eaf4003c80e231046c19e4f7e1bea218aa", "generation_seconds_batch": 18.83372278395109, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.437288999557495, "target_z": 6.187499863860602, "ce": 6.300607204437256, "genuineness": 4.055472373962402, "identity": 0.4206532835960388, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hin.", "wer": 0.0625, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/dd1664c9f4c5846033c459a1579dbd797c764ac1179488cc427dc78ede99de37.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "dd4777245f5ef22bd0e800775654dc1198c7303341416422cbce420198e7d25e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fee309ac681fd075673ed648d8f38bab56d909f231583c6b7ec4199f2785ff1e", "generation_seconds_batch": 19.452696182997897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8052342534065247, "target_z": 1.125000014330463, "ce": 6.284721851348877, "genuineness": 3.7667744159698486, "identity": 0.2219523787498474, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/dd4777245f5ef22bd0e800775654dc1198c7303341416422cbce420198e7d25e.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "dd682cfe9ad7e879c47d3c77e72a6480391b47317a2ba587eebfd844de3b9406", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d6f2cade0e0fc06391c63e340234123ab4785858b0e3e9e8bf0f910781de3756", "generation_seconds_batch": 13.958332704030909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6183908581733704, "target_z": 0.7656250197043867, "ce": 6.109982967376709, "genuineness": 4.068024158477783, "identity": 0.5940261483192444, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/dd682cfe9ad7e879c47d3c77e72a6480391b47317a2ba587eebfd844de3b9406.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": "de654b029b0efb5cf40ca80b05e6c8ca48231075cf412266482571f81da187d4", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Someone moved the little blue chair.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f209288ebb763c7110b00fb12638abfe1e92a151d49843ca1f9b7a742aa18616", "generation_seconds_batch": 14.889388252981007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3828057050704956, "target_z": 0.3125000214956945, "ce": 6.3641486167907715, "genuineness": 4.293961524963379, "identity": 0.2952343821525574, "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_Pride/de654b029b0efb5cf40ca80b05e6c8ca48231075cf412266482571f81da187d4.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "de75e55fbaf0dc659516bcf7e1074d79e12fd1d3d5034960d4eb6f804c7940fb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "de3a59b0fb299435d108022b53a6fa60391d408c8a2bc0c50707f95b6d524607", "generation_seconds_batch": 21.742597217089497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6549471616744995, "target_z": 0.8359374937304225, "ce": 6.173524379730225, "genuineness": 4.344170093536377, "identity": 0.6489952802658081, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/de75e55fbaf0dc659516bcf7e1074d79e12fd1d3d5034960d4eb6f804c7940fb.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": "deb00b40af64536f92d67689fc5b37e4724b3722acfa153dff24dc2d5a07a240", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e3e591fe29c40994dcf12b231a0b8ee02c07c9d9afc6788a1311f5c9ea6c462", "generation_seconds_batch": 16.79895474901423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3421875536441803, "target_z": 0.23437498029561338, "ce": 6.221180438995361, "genuineness": 3.9927117824554443, "identity": 0.5591468214988708, "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_Pride/deb00b40af64536f92d67689fc5b37e4724b3722acfa153dff24dc2d5a07a240.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "defca8ed480b97f0e06513fd1fa3e5517779d6bf158e03e7c435c2dae980a009", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2d748ae49dd66379fc456231e8e4b4ced393f35f7aa6d721aef3fc01d9ed8ecb", "generation_seconds_batch": 19.565635862061754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1139320135116577, "target_z": 1.7187499605912266, "ce": 6.062326908111572, "genuineness": 3.6914620399475098, "identity": 0.419534832239151, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/defca8ed480b97f0e06513fd1fa3e5517779d6bf158e03e7c435c2dae980a009.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "e01e7d2ebc5a73e1be6167880d9bd3ff6dfb916af5a724c32ca88139d656214b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "20b2a7d48fd5df6e257acad204de446567fb347ef2f7f6066601e3524e85ce29", "generation_seconds_batch": 21.180813926970586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.606205403804779, "target_z": 0.7421874901478067, "ce": 6.205295085906982, "genuineness": 4.432034492492676, "identity": 0.6293013095855713, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e01e7d2ebc5a73e1be6167880d9bd3ff6dfb916af5a724c32ca88139d656214b.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "e02def728f807d791253635e34412aa3e35b7e2ac789c65869082e8b2d2791ab", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8b8abf43f47c3bc5c80f058dc066a362d035c2a8a4e8e81ec86b97af8930769f", "generation_seconds_batch": 18.708674637950025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7341524958610535, "target_z": 0.988281206560784, "ce": 6.0305562019348145, "genuineness": 4.093128204345703, "identity": 0.5170549154281616, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e02def728f807d791253635e34412aa3e35b7e2ac789c65869082e8b2d2791ab.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": "e049f984e31f4eac6c33e8cd5088572fd7ccdca72072ac3f5ac2795589811b1c", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e42f4b57c47e7ea2e754458d5cfae39fbebfa6b8f0f1e0654c5fc56f3de7a51d", "generation_seconds_batch": 14.8054414720973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5274429321289062, "target_z": 4.43749994984338, "ce": 6.133810997009277, "genuineness": 4.306513786315918, "identity": 0.5571979284286499, "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_Pride/e049f984e31f4eac6c33e8cd5088572fd7ccdca72072ac3f5ac2795589811b1c.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "e15da5b230bd304e0232689a4ed3ed032925ea22ed00192c01078091c9d96610", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c1fe30638fade9bb7da5a152b1f368349888aec51cb93f3aa7e931c9a272ea9e", "generation_seconds_batch": 18.427111599012278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44068652391433716, "target_z": 0.4238281149238932, "ce": 6.23706579208374, "genuineness": 4.444586753845215, "identity": 0.6512300968170166, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e15da5b230bd304e0232689a4ed3ed032925ea22ed00192c01078091c9d96610.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "e1e9a293043d894f7016802e150c9c8e6bb66f4b75801b6be2fccfa8ecc58d7c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3e4111dae87d80145409f83aa937291a23314e14ba0b753b1b41988c045dd42c", "generation_seconds_batch": 19.438440328929573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5655872821807861, "target_z": 0.6640625062695775, "ce": 6.23706579208374, "genuineness": 4.306513786315918, "identity": 0.6476671695709229, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e1e9a293043d894f7016802e150c9c8e6bb66f4b75801b6be2fccfa8ecc58d7c.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "e226a03bb4cd583ca31c0620f67a5acd129f32681822fe3da098c2696a5d9e54", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "afd76c23aef73e2d7b1f1ccdd044f8c065b3e54679aa3b374dccf6e6d8db8b86", "generation_seconds_batch": 21.039873359026387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.129385232925415, "target_z": 3.6718749014780667, "ce": 6.308549880981445, "genuineness": 3.9927117824554443, "identity": 0.500860333442688, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam herum.", "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_Pride/e226a03bb4cd583ca31c0620f67a5acd129f32681822fe3da098c2696a5d9e54.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "e235a4f1d052f06b9a3a9264d9c257d38e58ba8994e8e9616368ea87d15b36ea", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ffff7d38a10eba17040d9a86ac4ebbfab3176e2b3e79d46c1c9b590ed6b10459", "generation_seconds_batch": 19.45364417496603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.292651891708374, "target_z": 2.0625001648003245, "ce": 6.062326908111572, "genuineness": 4.017816066741943, "identity": 0.5554652214050293, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e235a4f1d052f06b9a3a9264d9c257d38e58ba8994e8e9616368ea87d15b36ea.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "e29445fe764ac6470a83c6917525fc36f4875364f0fc67182b13085529aa6b21", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c3cfd1bc2b27ef9068223ecccb7469b6dcf6e38e3fa9c93aaab08a7a8dc10d3b", "generation_seconds_batch": 19.7708992670523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.760554313659668, "target_z": 1.0390625206000406, "ce": 6.1894097328186035, "genuineness": 4.005263805389404, "identity": 0.19102692604064941, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e29445fe764ac6470a83c6917525fc36f4875364f0fc67182b13085529aa6b21.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "e2c7417622882863302ffafe4a20eeb32dd4b2c029be7c108332ef90f5c32e4b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6126a1318d110f9739efe3475076c407855d680c502fbd130ca30de503d81cc6", "generation_seconds_batch": 20.53687378705945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3122316896915436, "target_z": 0.1767578061184657, "ce": 6.173524379730225, "genuineness": 4.137060642242432, "identity": 0.3230530619621277, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e2c7417622882863302ffafe4a20eeb32dd4b2c029be7c108332ef90f5c32e4b.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "e330fffa86fc5aa82f40e8dacb6d2b3c4794dabfd7dc830364639ae5ebbb596d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2752012251a47b577cc5b51c2b1b2012a1f67674067e6fc26f312599caf4a16b", "generation_seconds_batch": 22.610170526080765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.991283655166626, "target_z": 3.40625002507831, "ce": 6.260893821716309, "genuineness": 3.9550557136535645, "identity": 0.6803330183029175, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e330fffa86fc5aa82f40e8dacb6d2b3c4794dabfd7dc830364639ae5ebbb596d.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "e3b7fbdf75cf9e79a3339638a5c187a533d9f8958bbf25c3a020c13085e421bb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6944738bad9ba005e16073d1aa97928f34c9b1b76c7e7721413d0640b2739251", "generation_seconds_batch": 18.547573003103025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.08064341545105, "target_z": 3.5781247832517473, "ce": 6.1020402908325195, "genuineness": 3.9425034523010254, "identity": 0.6585786938667297, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e3b7fbdf75cf9e79a3339638a5c187a533d9f8958bbf25c3a020c13085e421bb.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "e47340df10642d6e82972db1b9e301574b86c3ae94625c4a542a7ab69756bac1", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "73685ac3d29c5919d9b36d1eaf5945f8457290693b9396208165abd63687c713", "generation_seconds_batch": 18.557461034040898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8539760112762451, "target_z": 1.2187500179130788, "ce": 6.157639026641846, "genuineness": 3.9425034523010254, "identity": 0.4060310125350952, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e47340df10642d6e82972db1b9e301574b86c3ae94625c4a542a7ab69756bac1.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": "e4c8efb7ab8abaa511e08a86f49ea01830e285b2f1460adea5bf260b42dae495", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I wrote the number on the envelope.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c05e1c13f5bf4ce6bd55510d398c114a450bbe5d1f43aba30a72dff7267478f", "generation_seconds_batch": 16.0765014749486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3162286281585693, "target_z": 4.031249896104144, "ce": 6.348263263702393, "genuineness": 3.8295347690582275, "identity": 0.07063744962215424, "hypothesis": "I wrote the number on the envelope. Rate it carefully, and check the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e4c8efb7ab8abaa511e08a86f49ea01830e285b2f1460adea5bf260b42dae495.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "e52f00ab95f0318f89a247eed617fb0be5cb18ef549be227bdafe8bab019fc30", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cd8337ed7bea8be0835c8a9ab6746ed1fa7ef64b28f499584acd3f860d6267f7", "generation_seconds_batch": 18.928506533964537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7443070411682129, "target_z": 1.0078124811912672, "ce": 6.229123115539551, "genuineness": 4.017816066741943, "identity": 0.7006866931915283, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e52f00ab95f0318f89a247eed617fb0be5cb18ef549be227bdafe8bab019fc30.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "e570a727c3dba95e3b563e996fa04deb8f39fc4a3fb7f6778b06a51a2432dd0d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "508dc9a3806af23b764ad173eaeabfb67b1006e181cc37abafa0745a52ec4b8a", "generation_seconds_batch": 24.121200083987787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6338441371917725, "target_z": 2.7187500752349307, "ce": 6.141753673553467, "genuineness": 4.18099308013916, "identity": 0.2754899263381958, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e570a727c3dba95e3b563e996fa04deb8f39fc4a3fb7f6778b06a51a2432dd0d.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "e573c65d8750094fa900cd5bb601dda614e504b5382cbe4276b6088128a7568b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "40006f61d5c3e7759dacf204345af4c9becd6fc6fa52234df5c5d021a6da4895", "generation_seconds_batch": 19.626927951001562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3848366141319275, "target_z": 0.31640627642179114, "ce": 6.181467056274414, "genuineness": 4.13078498840332, "identity": 0.6196123361587524, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e573c65d8750094fa900cd5bb601dda614e504b5382cbe4276b6088128a7568b.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": "e5d940d2c27d3701b64465562ff3414090c9497c6ae7ba59444b256783e7eeaf", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "044638cc453a9af4d53c86f3c6f24e017af9145850a1fab0332d81db964565ef", "generation_seconds_batch": 14.510694858036004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6915034651756287, "target_z": 0.9062499677564583, "ce": 6.24500846862793, "genuineness": 4.068024158477783, "identity": 0.6316603422164917, "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_Pride/e5d940d2c27d3701b64465562ff3414090c9497c6ae7ba59444b256783e7eeaf.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "e5ec77c4cffb14bdb64c7a6399020878275a6781125ea86992159ea84a9093d5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b505092a41b14224d4464fd4a1cbb3374bc2f88d1020374f5f57360b48622a4b", "generation_seconds_batch": 18.811872706981376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.494948387145996, "target_z": 4.374999871025833, "ce": 6.268836498260498, "genuineness": 4.080576419830322, "identity": 0.5388749241828918, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle connaît.", "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_Pride/e5ec77c4cffb14bdb64c7a6399020878275a6781125ea86992159ea84a9093d5.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": "e5f9e60be446e08540ce13f205ddbe2ea61a3957826276dd01a415e510064232", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "db87889b53c58259729831074182b4ef9bba300b21db667e86a3d2eeaed54f8a", "generation_seconds_batch": 22.758226522011682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4772428274154663, "target_z": 0.494140588949929, "ce": 6.260893821716309, "genuineness": 4.243753433227539, "identity": 0.7297664880752563, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e5f9e60be446e08540ce13f205ddbe2ea61a3957826276dd01a415e510064232.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "1bb8a06a3e811d4bc29c6e7d1103935efef136eda79083720146f5dae316b83c", "generation_seconds_batch": 14.14030745497439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2954767048358917, "target_z": 0.1445312316390943, "ce": 6.324435234069824, "genuineness": 4.268857479095459, "identity": 0.2965225279331207, "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_Pride/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "e7249152a2ac62fd1f2347e75a6d0a67830fe99e00b98f6e8295c7e8e7aa7305", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c5c6f0a17c41d167af855eac8a63f7d05c1d5addb0122548422a6cd0cf7e25b9", "generation_seconds_batch": 13.62478953693062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5932259559631348, "target_z": 2.6406249767129975, "ce": 6.173524379730225, "genuineness": 3.9801597595214844, "identity": 0.6879154443740845, "hypothesis": "J'ai trouvé la 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_Pride/e7249152a2ac62fd1f2347e75a6d0a67830fe99e00b98f6e8295c7e8e7aa7305.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "e726f7f3e4cf4cfcbd7905d72a23f274161d36b2353e805d3be7e6dbcf63495b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "02ddbc4127d2c9f92ffd0d50b2e007850e436abfcd5fee26775f4155921f1630", "generation_seconds_batch": 18.54090722789988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5526078939437866, "target_z": 2.5625001074784723, "ce": 6.125868320465088, "genuineness": 3.9048471450805664, "identity": 0.7047384977340698, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e726f7f3e4cf4cfcbd7905d72a23f274161d36b2353e805d3be7e6dbcf63495b.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": "e751f4a0e5f0554882d53d61a357889ede57dee48201c924d0659d8f5faced8a", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0f8efb1c94e2d6a223bdcc2ac8721a64cc07973d0c503315430c73ef00bab4c", "generation_seconds_batch": 14.734632453066297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47419649362564087, "target_z": 0.48828126388263604, "ce": 6.149696350097656, "genuineness": 4.068024158477783, "identity": 0.7135114669799805, "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_Pride/e751f4a0e5f0554882d53d61a357889ede57dee48201c924d0659d8f5faced8a.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "e765f4ba3c6042c78c23418bd7e980a9a7dd7bbc2246562fca71c05873e3d4b6", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "316e8ce1dac13b12d87f64e55b12a212ff88fd4e174bf74f8542f5734a85050f", "generation_seconds_batch": 19.653450220939703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0002013444900513, "target_z": 1.50000014330463, "ce": 6.2767791748046875, "genuineness": 3.848362922668457, "identity": 0.4189675450325012, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e765f4ba3c6042c78c23418bd7e980a9a7dd7bbc2246562fca71c05873e3d4b6.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "e7a4f41b0d1d0f0bf1e97643eb6d4db4833178d9058a75c1b9070489c0b0b170", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d1768c1f9a5e97f1c8c821f9a7d07be751fdbfccb9071b2930d4e07f51c1090d", "generation_seconds_batch": 21.867657708004117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.203291893005371, "target_z": 1.8906249480520716, "ce": 5.967014789581299, "genuineness": 4.061748504638672, "identity": 0.5613284111022949, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/e7a4f41b0d1d0f0bf1e97643eb6d4db4833178d9058a75c1b9070489c0b0b170.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": "e81a364ff682ad775aa6c251e74487fcf867485e3a644bc84faf070a5070852e", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "449c919557dbb0bf5e71cc453a7bb8391381c3b4ffeb5be7393b171c31b338a4", "generation_seconds_batch": 19.323690138058737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.853182077407837, "target_z": 3.1406251486785535, "ce": 6.419747352600098, "genuineness": 3.6977379322052, "identity": 0.2926512360572815, "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_Pride/e81a364ff682ad775aa6c251e74487fcf867485e3a644bc84faf070a5070852e.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "e8d55e81fdf2be0c3f3434afc3e1b85eaab4c0c968f201c3f6e1dc3ba11706af", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c254836d79330baef394de7e3190b7966b236c2eef8c871c287cbd885104b000", "generation_seconds_batch": 15.523317924933508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4670883119106293, "target_z": 0.47460937164129774, "ce": 6.3641486167907715, "genuineness": 4.375550270080566, "identity": 0.4880194664001465, "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_Pride/e8d55e81fdf2be0c3f3434afc3e1b85eaab4c0c968f201c3f6e1dc3ba11706af.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "713758b6a4c85aca9a1b6f7489254842461413aeb54d5640befcebfa658d2885", "generation_seconds_batch": 13.725433557992801, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3604657053947449, "target_z": 0.2695312173086313, "ce": 6.316492557525635, "genuineness": 4.369274139404297, "identity": 0.6853337287902832, "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_Pride/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.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": "e9f1e885fbb5cb19acccb92ef1ac3e8d63f8cb32b09fb14ec1ca641efb87d55e", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4feb5c8e0ce3a5c182dfb7fcae0ae6988a5cf43addb0335151a605bef740dcb9", "generation_seconds_batch": 16.939518630038947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5696491003036499, "target_z": 0.6718750161217709, "ce": 6.24500846862793, "genuineness": 3.835810661315918, "identity": 0.44083553552627563, "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_Pride/e9f1e885fbb5cb19acccb92ef1ac3e8d63f8cb32b09fb14ec1ca641efb87d55e.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": "ea26079f4cd613a45da8c0e7bccba48d9fece50b188d77c50a6e8774b7b7ef38", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f329da0b5abdcc555216dcc3976c748f682f776fc511cf40a545f11a8e81b81", "generation_seconds_batch": 15.954988455981947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46404194831848145, "target_z": 0.4687499892521528, "ce": 6.062326908111572, "genuineness": 4.20609712600708, "identity": 0.7352944612503052, "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_Pride/ea26079f4cd613a45da8c0e7bccba48d9fece50b188d77c50a6e8774b7b7ef38.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "ea4d3562c00d30e908685b93524dc07269eaf103ebf70ba3a939026c0ada2d80", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e85192363492b5d86b1814eb426f84a71ea9c757ce97e7f4b8fe751e6dd8cc41", "generation_seconds_batch": 18.88034257898107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9473977088928223, "target_z": 1.398437515226117, "ce": 6.181467056274414, "genuineness": 3.948779582977295, "identity": 0.5470305681228638, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ea4d3562c00d30e908685b93524dc07269eaf103ebf70ba3a939026c0ada2d80.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "ea80978a33ac596fdbca8a80dd4ef58e4d439fb7fe19184624d9ff5db78221e4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "09a3943acc7dbcfa3fcb73fc90952b963b9cf3dc2ad0f591e49d8cd6f55622f8", "generation_seconds_batch": 22.65488299203571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3088990449905396, "target_z": 2.09374997492169, "ce": 5.919358730316162, "genuineness": 4.13078498840332, "identity": 0.5109395980834961, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "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_Pride/ea80978a33ac596fdbca8a80dd4ef58e4d439fb7fe19184624d9ff5db78221e4.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "eab67f652f87aa22bef3693359d56d7e602cd4bb7ce99ae9a182471e9ada5ded", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18ba79cdc4f173c050203d201c25671d664ac89ac0862423940e4824ee5127d2", "generation_seconds_batch": 18.593736000941135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.028633952140808, "target_z": 1.5546874829825752, "ce": 6.149696350097656, "genuineness": 4.582659721374512, "identity": 0.5658590793609619, "hypothesis": "Je trouvai la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/eab67f652f87aa22bef3693359d56d7e602cd4bb7ce99ae9a182471e9ada5ded.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": "eb085acd5604dfe495340d40219f1add34c936ba4d8acbf1202671e9626ca4d3", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "54382b28f9f4f677cb1f4f9c4ca18d7cb8595cf8e9629dac7d0db8126af52b01", "generation_seconds_batch": 13.809268933022395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47622740268707275, "target_z": 0.4921875188087327, "ce": 6.173524379730225, "genuineness": 4.306513786315918, "identity": 0.5628209710121155, "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_Pride/eb085acd5604dfe495340d40219f1add34c936ba4d8acbf1202671e9626ca4d3.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "eb1f9488959c64c532f9658087cc5c1316da0dfe2952633fb741883bb1b670fb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c600be3c9a80e04f192fb5e7b41076605bb6304817cd19d0d30d2f1a73a8ef2d", "generation_seconds_batch": 20.372071170946583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5363606214523315, "target_z": 2.531250068069699, "ce": 6.109982967376709, "genuineness": 4.231201171875, "identity": 0.7118395566940308, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/eb1f9488959c64c532f9658087cc5c1316da0dfe2952633fb741883bb1b670fb.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "eb89a9f84906c0b191d8a4b1eee6de291bd6a098fbc72e2beebb42ea97255851", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0e2a3516128b09939e33be319fb406b05b9a711edd8b597c93ff65e17fcb113f", "generation_seconds_batch": 14.201262893970124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1058083772659302, "target_z": 1.70312494088684, "ce": 6.165581703186035, "genuineness": 3.9299514293670654, "identity": 0.6887652277946472, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/eb89a9f84906c0b191d8a4b1eee6de291bd6a098fbc72e2beebb42ea97255851.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "eba622eaf41963e3ac86c51c971c848c4896e75f4e048b736259c7465fb67e8f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5f72c81ca5fa6b274f063c460ad24e98a97d24e26869ba0e478b42bd7157cafa", "generation_seconds_batch": 19.52123998303432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.040025472640991, "target_z": 3.50000014330463, "ce": 6.300607204437256, "genuineness": 3.886019229888916, "identity": 0.4189618229866028, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/eba622eaf41963e3ac86c51c971c848c4896e75f4e048b736259c7465fb67e8f.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "ebbc10b8767a24f82ea5c53cfbf859754112443e20d87f5bb3cc0b40c88b7808", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d6e4f9afbc4844cf3bac7816a08de7fda3ca6202a471ba3ec6b91a19971390eb", "generation_seconds_batch": 16.284089324064553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6346380710601807, "target_z": 0.7968749444694558, "ce": 6.348263263702393, "genuineness": 4.13078498840332, "identity": 0.225843146443367, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ebbc10b8767a24f82ea5c53cfbf859754112443e20d87f5bb3cc0b40c88b7808.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": "ebc07a17673b83a1599337d52d1c7abc376635da0806a1270919abb8fa687a88", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc25eb3d35043331b3d08d9a58c2378e71fad97b7b6ad6af5ad4d7496e1f5349", "generation_seconds_batch": 19.323690138058737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7638221979141235, "target_z": 2.9687501612177085, "ce": 6.24500846862793, "genuineness": 3.835810661315918, "identity": 0.517715334892273, "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_Pride/ebc07a17673b83a1599337d52d1c7abc376635da0806a1270919abb8fa687a88.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "dc35b3ebf8195433d9ef58dc5a8af01aad4b44577ee3d87365da384e80499ecc", "generation_seconds_batch": 14.633490712032653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20662455260753632, "target_z": -0.026367192090226428, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.7163019180297852, "hypothesis": "La roue tourne à gauche après le pont. Continue, jusqu'à la petite barrière en bois. Je t'attendrai je t'attendrai de l'autre côté.", "wer": 0.15, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "ec07a880041018ffa5904447579398249639dfead706cb65ad1e527e3f5540eb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a4f23482136ffb91849951ef238f36bb85ba47886ed3d91191bfb2caccf65857", "generation_seconds_batch": 14.132867455016822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4063825607299805, "target_z": 2.2812499820869214, "ce": 6.213237762451172, "genuineness": 4.2751336097717285, "identity": 0.5680506229400635, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ec07a880041018ffa5904447579398249639dfead706cb65ad1e527e3f5540eb.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "ec3340fe54eb82279e88965e742f36d3bfee0c0ff99daad1c5fb608cde42562f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0929c3485378e9fafff87aeeecdab19836e260ea36a5add06f559d677160c5ea", "generation_seconds_batch": 19.22525927599054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6305763125419617, "target_z": 0.7890625492609665, "ce": 6.1894097328186035, "genuineness": 4.3504462242126465, "identity": 0.19893361628055573, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ec3340fe54eb82279e88965e742f36d3bfee0c0ff99daad1c5fb608cde42562f.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "ecf10dd33eea3ff7c639f0578dd48c6ed81f9a51bb3fa8e2d1312eb7d0a26d51", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2d53407a97f91f5ce2c056fe919987c9f4f5308e3258aa42d759bb1b6d728545", "generation_seconds_batch": 21.931552411057055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6508853435516357, "target_z": 0.8281249838782291, "ce": 5.967014789581299, "genuineness": 3.8044304847717285, "identity": 0.3964639902114868, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ecf10dd33eea3ff7c639f0578dd48c6ed81f9a51bb3fa8e2d1312eb7d0a26d51.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "ed481502e9df3e2198733bccacad79c71d35abffd028430a10c0a078246cecb4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a35dd0ed2761345d8870b3467d9ab9c95dc185602dcde104e1111682d0895d63", "generation_seconds_batch": 14.907041014055721, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5534018278121948, "target_z": 0.6406249767129977, "ce": 6.006728172302246, "genuineness": 4.193545341491699, "identity": 0.6945674419403076, "hypothesis": "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_Pride/ed481502e9df3e2198733bccacad79c71d35abffd028430a10c0a078246cecb4.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "ee3a171863cf8b732aca2132e10f911b3809596a83811ccbd95d9d31e7b828eb", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "215406d37f58fa484257ab101d0c71a5fa37b0b8509f4bb91bfd8e826c3d809c", "generation_seconds_batch": 18.853901631082408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7118125557899475, "target_z": 0.9453125170174248, "ce": 6.300607204437256, "genuineness": 4.093128204345703, "identity": 0.7665718793869019, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ee3a171863cf8b732aca2132e10f911b3809596a83811ccbd95d9d31e7b828eb.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": "eecb13b95f673cfe2368d832d227365b7ca2c01cab8fa9193a6b5e7c80382579", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d6a626bde63d38d3f69990a33f649f392b56d288c2879ad05cf580166740a23", "generation_seconds_batch": 23.074030383024365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34980344772338867, "target_z": 0.24902340760754985, "ce": 6.006728172302246, "genuineness": 3.9173994064331055, "identity": 0.7402563095092773, "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_Pride/eecb13b95f673cfe2368d832d227365b7ca2c01cab8fa9193a6b5e7c80382579.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "ef0388687ae3691b03dfa26adbf29475147d7869bc3b4af8dcbe45dfbe150f25", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d6f6cfb534a8a32a79d3ca0d3fa03b399ac0d31766588c4a4311cab3ea7c3721", "generation_seconds_batch": 14.526363937999122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9067795276641846, "target_z": 1.3203124167041838, "ce": 6.022613525390625, "genuineness": 3.8044304847717285, "identity": 0.6966506242752075, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ef0388687ae3691b03dfa26adbf29475147d7869bc3b4af8dcbe45dfbe150f25.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "ef68647215fa6c4719c1f96250cf817a1c8dd5ff63be03e9af4397d1594af97b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "38504050997ad8de44d730d1854a2d972466d378d707b928a0a2cd0d9e18e08e", "generation_seconds_batch": 18.893401367007755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8296051025390625, "target_z": 1.1718749587999189, "ce": 6.403861999511719, "genuineness": 4.532451152801514, "identity": 0.5961001515388489, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ef68647215fa6c4719c1f96250cf817a1c8dd5ff63be03e9af4397d1594af97b.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "ef72b03e77b6446ff7fd6cf78849b38fe3a85ba7cc331b46d5fc3146b3c21c18", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "702ba932d7e42f3b46a6204ceb70a57799f47ee159c3b53c50644267191f27ba", "generation_seconds_batch": 20.049703483004123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.126117467880249, "target_z": 1.7421874901478067, "ce": 5.816103935241699, "genuineness": 3.835810661315918, "identity": 0.4465337097644806, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ef72b03e77b6446ff7fd6cf78849b38fe3a85ba7cc331b46d5fc3146b3c21c18.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "f047badc29839697b704f154f652dbb70bca9d37c05d633cf393cdf8cf1c75f0", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eac7ae3c9f31cdda1824a0ca625d1891be61d83e6dfbc9ec9c6bbcc7d856c694", "generation_seconds_batch": 21.863680187030695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9717685580253601, "target_z": 1.4453124596955729, "ce": 6.229123115539551, "genuineness": 4.3504462242126465, "identity": 0.5832971930503845, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f047badc29839697b704f154f652dbb70bca9d37c05d633cf393cdf8cf1c75f0.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "f0830ab58345782ee0defa45d58a6fef0bbe9b2a60a6e3efaea6d24931ca0b34", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e2b1533dcfe5a4541523514d5c2a180964cd181e948e21195df835f319b4eaf3", "generation_seconds_batch": 16.522134819999337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8620995879173279, "target_z": 1.2343749229737613, "ce": 6.268836498260498, "genuineness": 4.20609712600708, "identity": 0.5556535720825195, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f0830ab58345782ee0defa45d58a6fef0bbe9b2a60a6e3efaea6d24931ca0b34.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "f0ea4a1197b3ae1dc5639c4d94ff73499b157b828df8997c769cc46fba37aa5c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "df1d6dbd5b5f96d6b143ac6b444915961e69f330b9ca5c06ca85f75ca3d52653", "generation_seconds_batch": 18.436440752004273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6041744947433472, "target_z": 0.7382812352217101, "ce": 6.372091293334961, "genuineness": 4.306513786315918, "identity": 0.43204474449157715, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f0ea4a1197b3ae1dc5639c4d94ff73499b157b828df8997c769cc46fba37aa5c.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "f10814cf174fb22a0fc93e5b0c9ddb831a401dbe018006d4ecb0553d415e521a", "bucket": "emo_Pride", "phase": "wording", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ae6eed920c0fa9a8655336ae95411fe60d550c8269dd60ddf97187862c80b3c6", "generation_seconds_batch": 17.142621400998905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5980817675590515, "target_z": 0.72656247044342, "ce": 6.197352409362793, "genuineness": 4.20609712600708, "identity": 0.6529446244239807, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f10814cf174fb22a0fc93e5b0c9ddb831a401dbe018006d4ecb0553d415e521a.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "f143fe17a01ef39dea6f3d7ea1a434fc5a9736c97fceeb2f4f8063389d72c368", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1d25071dd357944dca3db267b58c9a81c45f782ebd1de4b55e8d004da11b5bc1", "generation_seconds_batch": 13.865917143994011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35031118988990784, "target_z": 0.25, "ce": 6.1894097328186035, "genuineness": 4.231201171875, "identity": 0.7613987326622009, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f143fe17a01ef39dea6f3d7ea1a434fc5a9736c97fceeb2f4f8063389d72c368.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "f15c35a3e2090c2d945ef426debcfbc74d885f345ac10d6e9e22561e9c0f1a4e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d36cb7b2f403918fc6318f70960d9775c70bcde3f640d773f31419c00b24d12e", "generation_seconds_batch": 19.67428855097387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7016580104827881, "target_z": 0.9257812423869415, "ce": 6.157639026641846, "genuineness": 4.005263805389404, "identity": 0.6924631595611572, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f15c35a3e2090c2d945ef426debcfbc74d885f345ac10d6e9e22561e9c0f1a4e.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "df8a859a3ee75cd09aa6a1272c26c566f9be4f5e04b922f5df9465c78fc6f66b", "generation_seconds_batch": 14.417968613095582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6102672219276428, "target_z": 0.75, "ce": 6.284721851348877, "genuineness": 4.381826400756836, "identity": 0.5934858322143555, "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_Pride/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "f241935e2b907badbc6b17c1cd07b0c7da79dc8f0f8976f8ff977f36353d3ab3", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c59237d0c00426e169c28b01cca76b9d8c071fffa9b1625f16cc49c81f6b7a4b", "generation_seconds_batch": 19.833576151984744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.878346860408783, "target_z": 1.2656249623825346, "ce": 6.252951145172119, "genuineness": 4.068024158477783, "identity": 0.607703447341919, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f241935e2b907badbc6b17c1cd07b0c7da79dc8f0f8976f8ff977f36353d3ab3.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "f25f31a3e92b4ebb3a325e70cf086043afd6b2838d550164674e6669c4ebab3e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f66020134870cbc95d3fff47d3edfd63edf15f4c64394c151c89ecc9030fc937", "generation_seconds_batch": 14.166461859014817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9717685580253601, "target_z": 1.4453124596955729, "ce": 6.173524379730225, "genuineness": 3.9550557136535645, "identity": 0.5865596532821655, "hypothesis": "Ik heb het kleine noogje 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_Pride/f25f31a3e92b4ebb3a325e70cf086043afd6b2838d550164674e6669c4ebab3e.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "f266b16fa938a617938abc95755e042fa7a4eb811be74307439088343deb0a0f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7fa307ef4d04022e742d3dae18b4d955bf8471ca8770cec1f9ab310da23c1c60", "generation_seconds_batch": 14.12924280797597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2423219680786133, "target_z": 5.8124998495301385, "ce": 6.252951145172119, "genuineness": 3.9425034523010254, "identity": 0.45803868770599365, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f266b16fa938a617938abc95755e042fa7a4eb811be74307439088343deb0a0f.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "f2b66be7760de8e79511fbb3ee0d52500c73fcd7169618eeb251787296b16a6b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f71a6638730fecf49367617eb0a8b575bb18c430ad07ef73d9917a370854ca30", "generation_seconds_batch": 20.505787793081254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9717685580253601, "target_z": 1.4453124596955729, "ce": 6.308549880981445, "genuineness": 3.798154592514038, "identity": 0.21167230606079102, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f2b66be7760de8e79511fbb3ee0d52500c73fcd7169618eeb251787296b16a6b.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "f2bafa852ea0c6af5336c0c7fe51b7a96edcb62c5bb9989539e3bbeb3487612e", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6c404807936eedcf1f8292ffb7e0a70413a6547e42baa77bcaa74cfe70cad9a6", "generation_seconds_batch": 18.454116067034192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7971106171607971, "target_z": 1.1093749946260765, "ce": 6.173524379730225, "genuineness": 4.13078498840332, "identity": 0.6877657175064087, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f2bafa852ea0c6af5336c0c7fe51b7a96edcb62c5bb9989539e3bbeb3487612e.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "f2d509499cbd8d4ea651cb6834b2f92a8fff7b0dca29c24b08dc3c72ff5173ca", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f3cfccd9eacabc5bdb65ada5654e7292c2a763ce5bfb610cc33fa3e590a7c559", "generation_seconds_batch": 19.696029087994248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.478701114654541, "target_z": 4.3437498316170595, "ce": 6.141753673553467, "genuineness": 4.168440818786621, "identity": 0.5665140151977539, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f2d509499cbd8d4ea651cb6834b2f92a8fff7b0dca29c24b08dc3c72ff5173ca.mp3" }, { "id": "emo_Pride-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Pride-fr-0", "key": "f2ea21a0630f15cf2c98019ba143bd46912985ff05a60150124caa6b234be343", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "71be759806e09cd434f8286932582e2f6cac02cfae106173771013371d716578", "generation_seconds_batch": 19.787682521971874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6752562522888184, "target_z": 0.875000042991389, "ce": 6.157639026641846, "genuineness": 4.256305694580078, "identity": 0.589909553527832, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f2ea21a0630f15cf2c98019ba143bd46912985ff05a60150124caa6b234be343.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "f2ff8e417fa0324f794fd11fd9d40eb35ef362675409e19ba1fc2ee61bf5584f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a8156b87c9ffc995b922b78db1fb066b3bda2788bf9315779564310750d2613b", "generation_seconds_batch": 19.6449616139289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9311504364013672, "target_z": 1.3671874758173437, "ce": 6.1894097328186035, "genuineness": 3.8295347690582275, "identity": 0.32878851890563965, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f2ff8e417fa0324f794fd11fd9d40eb35ef362675409e19ba1fc2ee61bf5584f.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "f30c42397fda1691aaea05b75cfe9500b70d9d0da360c092e48655b2ca9c76de", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fe904b6f88618919edd43147edb956f89abe725125634249d3bda367ecc23c67", "generation_seconds_batch": 22.90883691003546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5046600699424744, "target_z": 0.5468749731303819, "ce": 6.09409761428833, "genuineness": 4.482243061065674, "identity": 0.455663800239563, "hypothesis": "He encontrado la cajita. Estaba junto en 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_Pride/f30c42397fda1691aaea05b75cfe9500b70d9d0da360c092e48655b2ca9c76de.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "f33fe076209bf37d8740d17a005250f6b8f7caf121e2e635eee75fb53a96bcda", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4cb21af7589c62fc8416ce1b99d53f1c39b28467c5ee8562bed839d9ab45723c", "generation_seconds_batch": 20.74951523495838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6569780707359314, "target_z": 0.8398437486565191, "ce": 5.967014789581299, "genuineness": 4.306513786315918, "identity": 0.7201817035675049, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f33fe076209bf37d8740d17a005250f6b8f7caf121e2e635eee75fb53a96bcda.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "f39b0d24f3640bedba7b0905a202a159bf41a4552a26d4c9ce5e11acf38b3cea", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6c7636582f94d532f669ad3f9dbef0751e5015132cb6cbc6214e41054ca6cfe6", "generation_seconds_batch": 22.617768086027354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0156545639038086, "target_z": 3.4531250841914702, "ce": 6.395919322967529, "genuineness": 4.256305694580078, "identity": 0.4174498915672302, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f39b0d24f3640bedba7b0905a202a159bf41a4552a26d4c9ce5e11acf38b3cea.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": "f3d9056802a7cb7f4c069abbbeb8b1e9c3281d2db9f44b91bece32327c7ff400", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "de9df4e51e615002376bd5bb0ab977994cdb84ee57b7bebd724990e6828766bf", "generation_seconds_batch": 13.789946026052348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5005982518196106, "target_z": 0.5390624632781885, "ce": 6.1894097328186035, "genuineness": 4.362998008728027, "identity": 0.5763024091720581, "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_Pride/f3d9056802a7cb7f4c069abbbeb8b1e9c3281d2db9f44b91bece32327c7ff400.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "f42bd0d389d44cf957edb9cf28329c6969064cdd0d228ba9459e7b6e69942a76", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f5258c532ef56ec35735d670fd02b2aeb652f58ad404ab8178b80ed13838011b", "generation_seconds_batch": 18.617735657957383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7849251627922058, "target_z": 1.0859374650694964, "ce": 6.356205940246582, "genuineness": 4.3127899169921875, "identity": 0.19107459485530853, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f42bd0d389d44cf957edb9cf28329c6969064cdd0d228ba9459e7b6e69942a76.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "f4787d6164e771b4512b6e51d09e97f7e1f96b95e2ebaa99d75c7c245f50d0f4", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5b580e041425ab3915de44bc29fba5e64d18d4b9de3482ec5e96ca675c8e990c", "generation_seconds_batch": 14.660800334997475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6143290400505066, "target_z": 0.7578125098521933, "ce": 6.109982967376709, "genuineness": 4.18726921081543, "identity": 0.6402844190597534, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f4787d6164e771b4512b6e51d09e97f7e1f96b95e2ebaa99d75c7c245f50d0f4.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "f54404f4f1dc4ee2494d0fba68448e27b6609f1177607b2f161869cfb2b1e5e1", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "87cffd34423a2375afd02b8bb7c4ef6c005aa5b42a08b154b4c1a5731aa423b5", "generation_seconds_batch": 19.471119842026383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4112383723258972, "target_z": 0.3671874758173437, "ce": 6.38797664642334, "genuineness": 4.432034492492676, "identity": 0.40433013439178467, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f54404f4f1dc4ee2494d0fba68448e27b6609f1177607b2f161869cfb2b1e5e1.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "f579c2abc33c6b43822baf85e67e4542658a1b05831fa436951ea26dc8d3f2c7", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9b1b8ac02f1f359cf6db989948b5a153484b4532e44c2804b71a19c4bcd36946", "generation_seconds_batch": 19.093734476016834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6874416470527649, "target_z": 0.898437457904265, "ce": 6.197352409362793, "genuineness": 4.2374773025512695, "identity": 0.5942320227622986, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f579c2abc33c6b43822baf85e67e4542658a1b05831fa436951ea26dc8d3f2c7.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "f58a07d55244501f923202b1c605ca2ec9a814bbecd0dfc6ab65a0634c8ba2ec", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "85b3844bbf8de0a47527c6d9580661701c8d1bc77efd1d45153f0c8fdcf34730", "generation_seconds_batch": 13.922116016037762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8499141931533813, "target_z": 1.2109375080608855, "ce": 6.356205940246582, "genuineness": 4.143336772918701, "identity": 0.7644627690315247, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f58a07d55244501f923202b1c605ca2ec9a814bbecd0dfc6ab65a0634c8ba2ec.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "f596baaaae1b744a9384eb740d15be9c3911500970c3fdf340338ef5b876c2fe", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ef63fe7ca20355f5a312aa654ce1994e42a66ed8e4e5686b7d26e9d85199249", "generation_seconds_batch": 21.306505053071305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9311504364013672, "target_z": 1.3671874758173437, "ce": 6.1894097328186035, "genuineness": 3.810706615447998, "identity": 0.06968946754932404, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f596baaaae1b744a9384eb740d15be9c3911500970c3fdf340338ef5b876c2fe.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "f635f2c465d4a1bd69a0cb513d4b231eff528c03a8973ce9ae9ada73379b8943", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5fa6b61a0dd2bc51fe02da3ef94d3e4db6e8216ae1abcac3217d3e3c5ce7ba97", "generation_seconds_batch": 21.147971534985118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.283734083175659, "target_z": 3.968749817286597, "ce": 6.24500846862793, "genuineness": 4.231201171875, "identity": 0.48043757677078247, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f635f2c465d4a1bd69a0cb513d4b231eff528c03a8973ce9ae9ada73379b8943.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": "f63d981086d5a8f618161d32a32059da0ee99748030561bbe5615041f7194477", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6e1c88f948de474ca893b4f45ef0bd9b45c8b08e09cc63c95d7318803803ef74", "generation_seconds_batch": 14.840154016041197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3413935899734497, "target_z": 2.156250053739236, "ce": 6.2767791748046875, "genuineness": 4.093128204345703, "identity": 0.5949816703796387, "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_Pride/f63d981086d5a8f618161d32a32059da0ee99748030561bbe5615041f7194477.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "f6cafb7cfaf61e3235a8114580422e143fcc5c4d6504521cd197a4806a844353", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0d5051420afc8a4c76e3874810a221ff7d589ce42b6cad0331f82e7424bdf0f1", "generation_seconds_batch": 18.961174075026065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8986559510231018, "target_z": 1.3046875116435013, "ce": 6.2767791748046875, "genuineness": 4.432034492492676, "identity": 0.4728130102157593, "hypothesis": "J'ai trouvé la 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_Pride/f6cafb7cfaf61e3235a8114580422e143fcc5c4d6504521cd197a4806a844353.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "f6fb1f789abaae7ed3dde196916b6a262324fe97be9c04a1652d850e1ccaa73b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "48fd28befb6824efee560fa1ff99f0c98e0b1ba85d3579465700334e3cd7bd8c", "generation_seconds_batch": 13.768702864996158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.894594132900238, "target_z": 1.2968750017913078, "ce": 5.911416053771973, "genuineness": 4.017816066741943, "identity": 0.3503754138946533, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "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_Pride/f6fb1f789abaae7ed3dde196916b6a262324fe97be9c04a1652d850e1ccaa73b.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "f6fcf2eeea5467b68efca9a8d5768cae922d6dcf8abeb56a9f35ed56082ce76d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3fd6925ea4d14a7666a1c355b449a60c5f7687a14cebdbd6564b28c72137feeb", "generation_seconds_batch": 21.306505053071305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8580378293991089, "target_z": 1.226562527765272, "ce": 6.054384231567383, "genuineness": 3.7040140628814697, "identity": 0.36703166365623474, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f6fcf2eeea5467b68efca9a8d5768cae922d6dcf8abeb56a9f35ed56082ce76d.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "f725d859eee0b4ca5ba7f758f6a892903acc6e55b1c3bc3eb4776124ac72a95b", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9aa17425cc371e627e5a3feaa9e1677352f0e6e162381e46953006a0357d74cc", "generation_seconds_batch": 18.441480853012763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8296051025390625, "target_z": 1.1718749587999189, "ce": 6.181467056274414, "genuineness": 4.545003414154053, "identity": 0.6474700570106506, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f725d859eee0b4ca5ba7f758f6a892903acc6e55b1c3bc3eb4776124ac72a95b.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "882b93a59189e6b6ed8b27d2b288d38dbc634b169525286c6342a6d457ad676a", "generation_seconds_batch": 14.37251830601599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3899138569831848, "target_z": 0.3261718564151808, "ce": 6.1894097328186035, "genuineness": 4.444586753845215, "identity": 0.6691153645515442, "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_Pride/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "f7e616e16badbfb0c4bda620b9e3b96caad36c9a420357a5a3c8755a5464d025", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "05c5001ee08c45dfff80c64b8b6d565dcce085c97fd824522ca87ba203ba70f1", "generation_seconds_batch": 15.017204146948643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.048943042755127, "target_z": 1.5937500322435418, "ce": 6.38797664642334, "genuineness": 4.243753433227539, "identity": 0.6719952821731567, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f7e616e16badbfb0c4bda620b9e3b96caad36c9a420357a5a3c8755a5464d025.mp3" }, { "id": "emo_Pride-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Pride-es-1", "key": "f7f62f145b58bbebb081e940f4073af0bc8dfe9da31904d6af69eee794c8d297", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c75459765356c1bdc88535ac913ce412cdcc051bd07aac50de5b4b52cc28f618", "generation_seconds_batch": 19.62302931700833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46607285737991333, "target_z": 0.4726562441782494, "ce": 6.181467056274414, "genuineness": 4.3881025314331055, "identity": 0.8102601766586304, "hypothesis": "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_Pride/f7f62f145b58bbebb081e940f4073af0bc8dfe9da31904d6af69eee794c8d297.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_Pride", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": "635f5d00c0dbb5f6e2b44bfe7d8c24c7bc7264e7ba33eadf598913e6ff511fe7", "generation_seconds_batch": 14.280613871989772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34624937176704407, "target_z": 0.2421874901478067, "ce": 6.300607204437256, "genuineness": 4.319066047668457, "identity": 0.5187689661979675, "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_Pride/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Pride-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Pride-en-0", "key": "f8762b4519d0f24873f0674b28c6db381871969a9969f38ad307ad09ee05f8c5", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] The door is still open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "daa74c3187eb33f19601421e5e74dfdfeb28719971e520b0df4a7e39d7fa1998", "generation_seconds_batch": 19.017863897955976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9027177691459656, "target_z": 1.3125000214956946, "ce": 6.125868320465088, "genuineness": 3.7416701316833496, "identity": 0.3007205128669739, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/f8762b4519d0f24873f0674b28c6db381871969a9969f38ad307ad09ee05f8c5.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": "f9b13744ea3509ad656def079a3c869cd2a004925e33906cb3c567c1293a21cb", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b6c75fe5b7b51e9cd724bdcdf19b28d638221611a964da9c98134b672daefc82", "generation_seconds_batch": 22.473764788010158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.933624267578125, "target_z": 5.218750017913079, "ce": 6.372091293334961, "genuineness": 4.118232727050781, "identity": 0.4922913908958435, "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_Pride/f9b13744ea3509ad656def079a3c869cd2a004925e33906cb3c567c1293a21cb.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "fac494e22a884b10665ccaae3455dd760f9cb4fae9e80525e55892f62f4f8639", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8d56952916dde9d6e798cdfabe3bfbe4e97bd6fa5a00e1e8d4188187548766f9", "generation_seconds_batch": 13.62478953693062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7150803804397583, "target_z": 2.875000042991389, "ce": 6.197352409362793, "genuineness": 4.231201171875, "identity": 0.7328455448150635, "hypothesis": "J'ai trouvé la 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_Pride/fac494e22a884b10665ccaae3455dd760f9cb4fae9e80525e55892f62f4f8639.mp3" }, { "id": "emo_Pride-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Pride-de-1", "key": "fac4ea2cfc192cdcf1efc4e8e21ffe3f0dad80348d11e5395f0a1b2c84492d0f", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "000f65f7f80f105ec41c4c2ecdffb512fca6e442e9586d287513a59dfa00f900", "generation_seconds_batch": 15.714072462986223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9019237756729126, "target_z": 3.2343750376174656, "ce": 6.332377910614014, "genuineness": 3.8546390533447266, "identity": 0.6275302171707153, "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_Pride/fac4ea2cfc192cdcf1efc4e8e21ffe3f0dad80348d11e5395f0a1b2c84492d0f.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": "fc72d29c9bc573c51290af88d30ee53709a3cb253d5319e3de257db67e47c05d", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "df9cbf0a3030da0fa3b7ce7a2be3950f9df99f5870b903be6d2e3089e9ec1903", "generation_seconds_batch": 22.398940818035044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5270000696182251, "target_z": 0.5898437773174451, "ce": 6.173524379730225, "genuineness": 4.168440818786621, "identity": 0.5266176462173462, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/fc72d29c9bc573c51290af88d30ee53709a3cb253d5319e3de257db67e47c05d.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": "fde9e2410b50281ebaf0bd80eecddc5945b66324b7fd955729b0c0a116265938", "bucket": "emo_Pride", "phase": "heldout", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6d5ed52fabe47a55f155aabc02bfb578b727c166c396cfefff37a1017dee30ae", "generation_seconds_batch": 14.668054795940407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6975961923599243, "target_z": 0.9179687325347482, "ce": 6.086154937744141, "genuineness": 3.8295347690582275, "identity": 0.7235255241394043, "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_Pride/fde9e2410b50281ebaf0bd80eecddc5945b66324b7fd955729b0c0a116265938.mp3" }, { "id": "emo_Pride-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Pride-nl-0", "key": "fe07735f31d7beb116419786c9474766f378b08bf95d0dbdce6c31ccf190e700", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] De deur staat nog open.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1cb96a8e80b49cf9fd4eaa29520055a9191f6423705bf7413bb5a8c7c79dea2b", "generation_seconds_batch": 18.614575150073506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1951682567596436, "target_z": 1.874999928347685, "ce": 5.998785495758057, "genuineness": 4.068024158477783, "identity": 0.6467382311820984, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/fe07735f31d7beb116419786c9474766f378b08bf95d0dbdce6c31ccf190e700.mp3" }, { "id": "emo_Pride-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Pride-de-0", "key": "fee17371be4a07ff2fc39d70407f27faee0ea389d1aa1b3bae75892cdd32849c", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "08938adb4e91ead883b063048240633943274e10db9c6cb946b19f1006b20765", "generation_seconds_batch": 16.420895869960077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0773757696151733, "target_z": 1.6484376012088948, "ce": 6.24500846862793, "genuineness": 4.105680465698242, "identity": 0.39928877353668213, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/fee17371be4a07ff2fc39d70407f27faee0ea389d1aa1b3bae75892cdd32849c.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "ff04639075d9b9717661d32401072e518dab4f6807ff3de550afc0221b811e59", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "43830fb6960da40e60818ce7a5c9ceb1561891493380bb27389959a296fbda17", "generation_seconds_batch": 21.77611526090186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5087218880653381, "target_z": 0.5546874829825752, "ce": 6.149696350097656, "genuineness": 4.582659721374512, "identity": 0.6996198296546936, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ff04639075d9b9717661d32401072e518dab4f6807ff3de550afc0221b811e59.mp3" }, { "id": "emo_Pride-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Pride-fr-1", "key": "ff2b47a03fe6822fc91d9cda251a5687b94d53c98ae33fc2b86acbb512fa883d", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "52992ffca08d8fa645c99ae879f1c479f57e4698778f19edf4159bcf1c98bc90", "generation_seconds_batch": 21.142344138002954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4794952869415283, "target_z": 2.421875159426401, "ce": 6.157639026641846, "genuineness": 4.193545341491699, "identity": 0.6179851293563843, "hypothesis": "J'ai trouvé la 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_Pride/ff2b47a03fe6822fc91d9cda251a5687b94d53c98ae33fc2b86acbb512fa883d.mp3" }, { "id": "emo_Pride-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Pride-nl-1", "key": "ff4a41ea78d919d6d164aaa2f6ed1fc2f94a9da896c13eefe959314154fd56de", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4d22812129e0338c5aed8554b37e0c02f438741b611b0dfbf80a5a4e12ef3395", "generation_seconds_batch": 19.71918007801287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5696491003036499, "target_z": 0.6718750161217709, "ce": 6.141753673553467, "genuineness": 4.18099308013916, "identity": 0.5416668653488159, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ff4a41ea78d919d6d164aaa2f6ed1fc2f94a9da896c13eefe959314154fd56de.mp3" }, { "id": "emo_Pride-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Pride-es-0", "key": "ff9dfc41ecdf6017306a551d1da86b96e3100d68a6930c8b6de3d313645c17ea", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d9413a43a610fd26b921b9a3e1677991561643db0f55a449451ff2cd0fc1fb66", "generation_seconds_batch": 21.77611526090186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.589958131313324, "target_z": 0.7109374507390335, "ce": 5.959072113037109, "genuineness": 4.15588903427124, "identity": 0.5873637199401855, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ff9dfc41ecdf6017306a551d1da86b96e3100d68a6930c8b6de3d313645c17ea.mp3" }, { "id": "emo_Pride-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Pride-en-1", "key": "ffaa973929262941f6086ab0543798918c2aa6d4796b430f023675b9c76e9275", "bucket": "emo_Pride", "phase": "grid", "candidate": "manual-b8282fc33fc9", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on precise articulation and clarity, using controlled projection to make the pride feel earned and meticulous rather than boastful.\nSCRIPT:\n(Initiate with crisp, deliberate consonants, projecting a focused sense of personal victory.) [3.2 seconds duration] I found the little box.\n(Sustain the mid-phrase with a clear, unwavering pitch contour that speaks to deep conviction.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a precise, resonant finality, letting the volume drop slightly while maintaining tonal authority.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "59dafa75ea1394d8660d672f16aae5ffbe50097b466640cfd32755916440ae9b", "generation_seconds_batch": 15.316499407053925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44576379656791687, "target_z": 0.4335937522391348, "ce": 6.2767791748046875, "genuineness": 4.344170093536377, "identity": 0.4187946915626526, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pride/ffaa973929262941f6086ab0543798918c2aa6d4796b430f023675b9c76e9275.mp3" }, { "key": "original-emo_Pride-de-0-seed1701-scale0.0", "bucket": "emo_Pride", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "db1d7d3fee32a4c307da2d577f1d238d3709c6d936fc615695786e9784d98b92", "task_id": "emo_Pride-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6833798289299011, "target_z": 0.8906249480520716, "ce": 6.1894097328186035, "genuineness": 4.3881025314331055, "identity": 0.5422273874282837, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/c51aa5843daa89d14d8d26d1.mp3" }, { "key": "original-emo_Pride-de-0-seed1701-scale0.5", "bucket": "emo_Pride", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "1bd26f29ad8880a0549c74ffcb96602e7e624da329959d1a1db0c915468d3e63", "task_id": "emo_Pride-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.7889869809150696, "target_z": 1.0937499749216897, "ce": 6.332377910614014, "genuineness": 4.331617832183838, "identity": 0.3670097887516022, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/f9ca710da9ca3a3ebb1778ff.mp3" }, { "key": "original-emo_Pride-de-0-seed1701-scale0.75", "bucket": "emo_Pride", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "47f23f842d80afa9a8cc9ae11b32cb25162981e4629e0f8be6fcba19dedce6f4", "task_id": "emo_Pride-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6610398888587952, "target_z": 0.8476562585087124, "ce": 6.157639026641846, "genuineness": 4.369274139404297, "identity": 0.4361498951911926, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/eec98465a69ac72e703cff43.mp3" }, { "key": "original-emo_Pride-de-0-seed1701-scale1.0", "bucket": "emo_Pride", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "43bcd45f499661df5371a4e7420f2f6cdec763cef2a5909e86c693a527c76345", "task_id": "emo_Pride-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.7260288596153259, "target_z": 0.9726561868563974, "ce": 6.1020402908325195, "genuineness": 4.356721878051758, "identity": 0.5600471496582031, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/a13a43dab5f71ab1bd7f4c8d.mp3" }, { "key": "original-emo_Pride-de-0-seed1702-scale0.0", "bucket": "emo_Pride", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "be199a2f8e29d8fb864edfb131b8201635001fb4bef968e7703c9324e485bde4", "task_id": "emo_Pride-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.8092960715293884, "target_z": 1.1328125241826563, "ce": 6.173524379730225, "genuineness": 4.381826400756836, "identity": 0.630867600440979, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/11f3b8f7207798478c6836eb.mp3" }, { "key": "original-emo_Pride-de-0-seed1702-scale0.5", "bucket": "emo_Pride", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "e6520289c45cfe2ba20eaa103382eac064833156bdac1bd60859d3c0c2413d15", "task_id": "emo_Pride-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.5777727365493774, "target_z": 0.6875000358261575, "ce": 6.157639026641846, "genuineness": 4.394378662109375, "identity": 0.4317203760147095, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/273a725e0eb0fd330cfb92bb.mp3" }, { "key": "original-emo_Pride-de-0-seed1702-scale0.75", "bucket": "emo_Pride", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "0569b80f6cefc6f156d7dea558212c661a60c1ab96a0aef74afd08ee041702f2", "task_id": "emo_Pride-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.5452781915664673, "target_z": 0.624999957008611, "ce": 6.221180438995361, "genuineness": 4.419482707977295, "identity": 0.487737238407135, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/06857afd1f0723747c97627a.mp3" }, { "key": "original-emo_Pride-de-0-seed1702-scale1.0", "bucket": "emo_Pride", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "3ad0bc1cf1a651b31934e365db22c8d16c6c2a1a1db9fd04830ed01a0146a65f", "task_id": "emo_Pride-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.5919890403747559, "target_z": 0.7148437056651301, "ce": 6.221180438995361, "genuineness": 4.595211505889893, "identity": 0.6728953719139099, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/f2d777a5189f6b6054c2841e.mp3" }, { "key": "original-emo_Pride-de-1-seed1701-scale0.0", "bucket": "emo_Pride", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "66c12e63a18c64e69bc00c9bbe63c02bbe7b5507bee8fedfd696688502d0d8d1", "task_id": "emo_Pride-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.040025472640991, "target_z": 3.50000014330463, "ce": 6.332377910614014, "genuineness": 4.231201171875, "identity": 0.4815390706062317, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/5fe9ce73e831129925e41da4.mp3" }, { "key": "original-emo_Pride-de-1-seed1701-scale0.5", "bucket": "emo_Pride", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "d11f26d0e490d20ed52b3987ac616af5351948dcf9f953ae15c2281ca81fe377", "task_id": "emo_Pride-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3576408624649048, "target_z": 2.1875000931480093, "ce": 6.427689552307129, "genuineness": 4.444586753845215, "identity": 0.3810911774635315, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/b825cca75070a4b6335a09fe.mp3" }, { "key": "original-emo_Pride-de-1-seed1701-scale0.75", "bucket": "emo_Pride", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "c57906e9a88a205bf104eed7e157aa5fdd3e412fada7bbd15d804a4d90bdeae1", "task_id": "emo_Pride-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.991283655166626, "target_z": 3.40625002507831, "ce": 6.284721851348877, "genuineness": 4.381826400756836, "identity": 0.5454825162887573, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/21bc43ff04093b383a383927.mp3" }, { "key": "original-emo_Pride-de-1-seed1701-scale1.0", "bucket": "emo_Pride", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "b7cf50dfb79edf27c30a43a5df6d5256ca9fec554a254fd2521a585890f70547", "task_id": "emo_Pride-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.87755286693573, "target_z": 3.1874999785043054, "ce": 6.4912309646606445, "genuineness": 4.582659721374512, "identity": 0.5528061389923096, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/20e9c91d739b5ce28e72a73c.mp3" }, { "key": "original-emo_Pride-de-1-seed1702-scale0.0", "bucket": "emo_Pride", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "d1cbce3d11ca901e210d6d5faddf68156d30455b0c295a750d459b68f5d557ae", "task_id": "emo_Pride-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.023778200149536, "target_z": 3.468750103895857, "ce": 6.419747352600098, "genuineness": 4.331617832183838, "identity": 0.5166082382202148, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/bd5caacea0edb1132d1b38c9.mp3" }, { "key": "original-emo_Pride-de-1-seed1702-scale0.5", "bucket": "emo_Pride", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "c7bb29269321a5be86a09bece1d1c1c9506ddadcd867d6a5f46f4d1bb52028d8", "task_id": "emo_Pride-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5363606214523315, "target_z": 2.531250068069699, "ce": 6.435632705688477, "genuineness": 4.319066047668457, "identity": 0.4214423596858978, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/b9a39c9ef00057aecf5a580c.mp3" }, { "key": "original-emo_Pride-de-1-seed1702-scale0.75", "bucket": "emo_Pride", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "23562875aabf57e584dc5aa1697aa610aef54609fa70b806da9e12119e060458", "task_id": "emo_Pride-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3576408624649048, "target_z": 2.1875000931480093, "ce": 6.340320587158203, "genuineness": 4.432034492492676, "identity": 0.537246584892273, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/bc15e5f4131c7e489e7077b6.mp3" }, { "key": "original-emo_Pride-de-1-seed1702-scale1.0", "bucket": "emo_Pride", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "d3d023b3e4ce2ea75ba77cb48c18207060cb4a196d0d990d3daabe058efca26f", "task_id": "emo_Pride-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5851024389266968, "target_z": 2.625000186296019, "ce": 6.395919322967529, "genuineness": 4.118232727050781, "identity": 0.4503110647201538, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/de/94a295602add00d261220685.mp3" }, { "key": "original-emo_Pride-en-0-seed1701-scale0.0", "bucket": "emo_Pride", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "91c84f28c93289e43c01ad6893d1080d764c4bded7b0155e1c2cca6764196a82", "task_id": "emo_Pride-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.719936192035675, "target_z": 0.9609375367218115, "ce": 6.221180438995361, "genuineness": 3.961331605911255, "identity": 0.3520054817199707, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/b782d9742d5705942a41fa6e.mp3" }, { "key": "original-emo_Pride-en-0-seed1701-scale0.5", "bucket": "emo_Pride", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "be7a104f88a30dfb5477fb2e1af6b298ce7da1d4472f26d4f67a8d9eb18992e5", "task_id": "emo_Pride-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.8092960715293884, "target_z": 1.1328125241826563, "ce": 6.1894097328186035, "genuineness": 3.873466968536377, "identity": 0.3682994842529297, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/c5c2c3b52fcf5784d082534b.mp3" }, { "key": "original-emo_Pride-en-0-seed1701-scale0.75", "bucket": "emo_Pride", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "3b1dca594e653a3aea884689e2cbe3ee3d7a2d3dbb40edc2fda7d803778e6368", "task_id": "emo_Pride-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.7727397084236145, "target_z": 1.0624999355129165, "ce": 6.316492557525635, "genuineness": 4.168440818786621, "identity": 0.3325473368167877, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/8133c50709057fd6932ba18e.mp3" }, { "key": "original-emo_Pride-en-0-seed1701-scale1.0", "bucket": "emo_Pride", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "4f559d9d4116a6062c27cfe58bb7a2081622c3c994f7e3fd5621dc04a544d995", "task_id": "emo_Pride-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.780863344669342, "target_z": 1.0781249552173031, "ce": 6.252951145172119, "genuineness": 4.218649387359619, "identity": 0.3247840404510498, "hypothesis": "The 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_Pride/en/11295d4b7064ad23ee4dadea.mp3" }, { "key": "original-emo_Pride-en-0-seed1702-scale0.0", "bucket": "emo_Pride", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "aa420bdd3201ee02a13df030b6a37f0f5fd92c62ec26adfba860e85c7d9d8ba9", "task_id": "emo_Pride-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.821481466293335, "target_z": 1.1562499390955323, "ce": 6.24500846862793, "genuineness": 3.9801597595214844, "identity": 0.26990193128585815, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/950d04b8780177f8a2b58fd8.mp3" }, { "key": "original-emo_Pride-en-0-seed1702-scale0.5", "bucket": "emo_Pride", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "026fdf11a6fa72831ab54d023c4a5d31fba1b06b048f187af667e449adc77435", "task_id": "emo_Pride-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.9433358907699585, "target_z": 1.3906250053739235, "ce": 6.221180438995361, "genuineness": 3.8922953605651855, "identity": 0.26489579677581787, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/e381247cf3aed1c7fa5847dc.mp3" }, { "key": "original-emo_Pride-en-0-seed1702-scale0.75", "bucket": "emo_Pride", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "64128fcc07514571e0c73554e2993f5a1b5c043d69b6beb8fc245f67c3ffcb24", "task_id": "emo_Pride-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.8174196481704712, "target_z": 1.148437429243339, "ce": 6.252951145172119, "genuineness": 3.8169827461242676, "identity": 0.4021943211555481, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/0d6996bf479efd7b19383202.mp3" }, { "key": "original-emo_Pride-en-0-seed1702-scale1.0", "bucket": "emo_Pride", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "3d09dc0670ff14b7137f9e2be39388e794f1d6f7607b8730522e2508cc96803c", "task_id": "emo_Pride-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.8499141931533813, "target_z": 1.2109375080608855, "ce": 6.292664527893066, "genuineness": 4.030367851257324, "identity": 0.2130371332168579, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/eecd5242498a8b7efca33891.mp3" }, { "key": "original-emo_Pride-en-1-seed1701-scale0.0", "bucket": "emo_Pride", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "8d6b2fd21707f8e8e5e6c09cf2384c0babcc7c1f0bf9f40d96225ab7bed316fb", "task_id": "emo_Pride-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.3442184627056122, "target_z": 0.23828123522171002, "ce": 6.2767791748046875, "genuineness": 4.607763767242432, "identity": 0.4859389662742615, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/18e351b30bb6b9feb8bf415a.mp3" }, { "key": "original-emo_Pride-en-1-seed1701-scale0.5", "bucket": "emo_Pride", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "e730d016f5d229caa67ec2effdc3be25b0231ed89c2ae3cf84250de2cbccf5e2", "task_id": "emo_Pride-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.36452752351760864, "target_z": 0.2773437271608246, "ce": 6.38797664642334, "genuineness": 4.570107460021973, "identity": 0.48525089025497437, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/76a46fcd44ac9f55f45d3ad5.mp3" }, { "key": "original-emo_Pride-en-1-seed1701-scale0.75", "bucket": "emo_Pride", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "d63a60d85c2a4d71d07dbe9ed726f5d20d47bb3b7d2e9e40bcdcc9c4070080e3", "task_id": "emo_Pride-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.404130220413208, "target_z": 0.35351564089785736, "ce": 6.308549880981445, "genuineness": 4.582659721374512, "identity": 0.44512709975242615, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/5fdffcae97eeae53f985cf67.mp3" }, { "key": "original-emo_Pride-en-1-seed1701-scale1.0", "bucket": "emo_Pride", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "7b2d9087e0c7137ea1176a3b82d7bd05f440c77687c3472527539f400c483fea", "task_id": "emo_Pride-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.37671297788619995, "target_z": 0.3007812567174045, "ce": 6.427689552307129, "genuineness": 4.532451152801514, "identity": 0.39142295718193054, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/c4e1c545990560938ae3fc63.mp3" }, { "key": "original-emo_Pride-en-1-seed1702-scale0.0", "bucket": "emo_Pride", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "9e9ae23ee72844a1212345e043fa530c9d6bafa406791df41f7cb48402ffe585", "task_id": "emo_Pride-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.4802892208099365, "target_z": 0.500000028660926, "ce": 6.427689552307129, "genuineness": 4.570107460021973, "identity": 0.3774716556072235, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/69e6c542d71cefc0d8f1735a.mp3" }, { "key": "original-emo_Pride-en-1-seed1702-scale0.5", "bucket": "emo_Pride", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "6c5ad8a190ab4f7e04fa15d1c1b247d18fa58b5e6183bb27887cca5fa951ea2e", "task_id": "emo_Pride-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.38382112979888916, "target_z": 0.31445309163689084, "ce": 6.316492557525635, "genuineness": 4.482243061065674, "identity": 0.49258604645729065, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/3742ed71d22cefa0699927c8.mp3" }, { "key": "original-emo_Pride-en-1-seed1702-scale0.75", "bucket": "emo_Pride", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "4116249d8277d7fe63375b1d75813011c537ebaa65b26d280e1186c0c6351d7b", "task_id": "emo_Pride-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.45693379640579224, "target_z": 0.45507815433266646, "ce": 6.268836498260498, "genuineness": 4.400654315948486, "identity": 0.4027966558933258, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/27235a070f25a1b60ee833d4.mp3" }, { "key": "original-emo_Pride-en-1-seed1702-scale1.0", "bucket": "emo_Pride", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "74cf2f0d24ccf6c3bbe6980b7b4a273213d1377fe7f4b0f51f941aa84d4229d7", "task_id": "emo_Pride-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.35335755348205566, "target_z": 0.25585938238914496, "ce": 6.395919322967529, "genuineness": 4.457139015197754, "identity": 0.35260725021362305, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/en/1749762601b95a70c7ccb3fc.mp3" }, { "key": "original-emo_Pride-es-0-seed1701-scale0.0", "bucket": "emo_Pride", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "386161fb7d34059c65d3990812f4dc07ffcac2b85c09cb559a921445f4b204d2", "task_id": "emo_Pride-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.8011724352836609, "target_z": 1.1171875044782698, "ce": 6.197352409362793, "genuineness": 4.168440818786621, "identity": 0.5971832275390625, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/1f9baff946c53a64bddaa796.mp3" }, { "key": "original-emo_Pride-es-0-seed1701-scale0.5", "bucket": "emo_Pride", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "92aba5f4d4ff6af5b9498373d6589a372ce4eab8e3a34a029e8c89f72ef8209a", "task_id": "emo_Pride-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.529030978679657, "target_z": 0.5937500322435417, "ce": 5.967014789581299, "genuineness": 4.093128204345703, "identity": 0.5626536011695862, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/35688a3b3da7f3ea31ce3ba9.mp3" }, { "key": "original-emo_Pride-es-0-seed1701-scale0.75", "bucket": "emo_Pride", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "86069c18afed68d49387313eee92f097c23812699ef298dd598c206d41ce3f82", "task_id": "emo_Pride-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6894725561141968, "target_z": 0.9023437128303616, "ce": 6.038498878479004, "genuineness": 3.9425034523010254, "identity": 0.5019552707672119, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/7f9105c288919156d368d67d.mp3" }, { "key": "original-emo_Pride-es-0-seed1701-scale1.0", "bucket": "emo_Pride", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "9d19aa80163ccac4adc6574702e05325b2abce4c4f55c33b56f420864a7c5d15", "task_id": "emo_Pride-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6102672219276428, "target_z": 0.75, "ce": 6.046441555023193, "genuineness": 4.049196243286133, "identity": 0.5437611937522888, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/5fdb07c622a98efa43783285.mp3" }, { "key": "original-emo_Pride-es-0-seed1702-scale0.0", "bucket": "emo_Pride", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "5f409d77b33c4767a92b8d154f1a975f50c04c3e2510c4a1b25af90ab3ce7d67", "task_id": "emo_Pride-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.589958131313324, "target_z": 0.7109374507390335, "ce": 5.95112943649292, "genuineness": 3.848362922668457, "identity": 0.39364928007125854, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/5c74f41b1ee3de88b3c9a268.mp3" }, { "key": "original-emo_Pride-es-0-seed1702-scale0.5", "bucket": "emo_Pride", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "bbb8a5147bc1c2ae2d70fa5ee21c61b8642b0b80ab6b2c55fbf4d69e32ce7bbb", "task_id": "emo_Pride-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.760554313659668, "target_z": 1.0390625206000406, "ce": 6.062326908111572, "genuineness": 4.193545341491699, "identity": 0.6668130159378052, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/5b20d31869fda8fa321dad62.mp3" }, { "key": "original-emo_Pride-es-0-seed1702-scale0.75", "bucket": "emo_Pride", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "28120b5710656ab2771b71c6e25834141b7ebe80939e20af9044e9c5ff213860", "task_id": "emo_Pride-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.7402452230453491, "target_z": 0.999999971339074, "ce": 6.022613525390625, "genuineness": 4.017816066741943, "identity": 0.4019401967525482, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/8db801d0b4d62d5d6d489ed2.mp3" }, { "key": "original-emo_Pride-es-0-seed1702-scale1.0", "bucket": "emo_Pride", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "33aafbdc99ca1521765f8af06bda8f565b11997f340aeb1aecd71ab8a272d99d", "task_id": "emo_Pride-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.5229382514953613, "target_z": 0.5820312674652518, "ce": 6.006728172302246, "genuineness": 3.9425034523010254, "identity": 0.6061917543411255, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/cbb818bcae95d0741c7e62e0.mp3" }, { "key": "original-emo_Pride-es-1-seed1701-scale0.0", "bucket": "emo_Pride", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "662c9129dc8c646244da2fe53caef522b3c692ea6f0d04684db3cb4a2132dc0d", "task_id": "emo_Pride-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.32492485642433167, "target_z": 0.2011718707456438, "ce": 6.0146708488464355, "genuineness": 4.469690799713135, "identity": 0.5476839542388916, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/c304120f77ff05fa224ccc90.mp3" }, { "key": "original-emo_Pride-es-1-seed1701-scale0.5", "bucket": "emo_Pride", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "1165aafdd6a07e4c4eba069966deabd3e0aeb6d049544568fcbbbaec7c7c249c", "task_id": "emo_Pride-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.5351237058639526, "target_z": 0.6054687970218318, "ce": 5.998785495758057, "genuineness": 4.469690799713135, "identity": 0.6252992749214172, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/15ee01d604924165213dfdad.mp3" }, { "key": "original-emo_Pride-es-1-seed1701-scale0.75", "bucket": "emo_Pride", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "4eefc934346ae24ede3b03d65e7208ea854d099e9c3a0838f84902a4d3eabce0", "task_id": "emo_Pride-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.47419649362564087, "target_z": 0.48828126388263604, "ce": 6.157639026641846, "genuineness": 4.243753433227539, "identity": 0.6202689409255981, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/a720643a43a29ed1560a2de3.mp3" }, { "key": "original-emo_Pride-es-1-seed1701-scale1.0", "bucket": "emo_Pride", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "36a85b296d6325adb71f36d621ef07769bbf130ea2311bc857bdf4bf9060309a", "task_id": "emo_Pride-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.4274856448173523, "target_z": 0.3984375152261169, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.6013702154159546, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/2b2497c2874826366ceb6f28.mp3" }, { "key": "original-emo_Pride-es-1-seed1702-scale0.0", "bucket": "emo_Pride", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "5c62852904d163718c14acc2e948cc3729e3a267d179b281668de192da91171a", "task_id": "emo_Pride-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6407307982444763, "target_z": 0.8085937092477459, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.479969322681427, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/87d4d717f29dade8e7f94a75.mp3" }, { "key": "original-emo_Pride-es-1-seed1702-scale0.5", "bucket": "emo_Pride", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "588ee71db825d443e88c7489d1f44754f5d726a75b9e9bbcfe69778225c6caf8", "task_id": "emo_Pride-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.5330927968025208, "target_z": 0.601562542095735, "ce": 6.165581703186035, "genuineness": 4.419482707977295, "identity": 0.5597215890884399, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/e8bc18e245b09fcc63bdbe20.mp3" }, { "key": "original-emo_Pride-es-1-seed1702-scale0.75", "bucket": "emo_Pride", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "48a4c897e3d9cc45e57ef81fe647016073ba17c8b881863ca0eef0603f106e39", "task_id": "emo_Pride-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.36249661445617676, "target_z": 0.2734374722347279, "ce": 6.348263263702393, "genuineness": 4.7332844734191895, "identity": 0.6629828214645386, "hypothesis": "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_Pride/es/5324dafc7907cd3904bbdbab.mp3" }, { "key": "original-emo_Pride-es-1-seed1702-scale1.0", "bucket": "emo_Pride", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "91c723e5528b8d176ece233b779ce8219c6830e5d0ebed45450673eed42da026", "task_id": "emo_Pride-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.39296022057533264, "target_z": 0.3320312388043258, "ce": 6.133810997009277, "genuineness": 4.482243061065674, "identity": 0.6456009149551392, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/es/03d424e71a23282bb02101c8.mp3" }, { "key": "original-emo_Pride-fr-0-seed1701-scale0.0", "bucket": "emo_Pride", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "7b9b31de68f46250046815d29eb59276e13da1d90ecd44d28ef357b0ab03f282", "task_id": "emo_Pride-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.5615254640579224, "target_z": 0.6562499964173842, "ce": 6.078212261199951, "genuineness": 4.375550270080566, "identity": 0.7632937431335449, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/dc06c8956e6350e7c36ec052.mp3" }, { "key": "original-emo_Pride-fr-0-seed1701-scale0.5", "bucket": "emo_Pride", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": 129, "seconds_generated": 10.32, "ended": true, "contract_sha256": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "f7bbfdd641360d1f65ebadc0b7f92c38ec0f58a3d42d666aea53a1037d054295", "task_id": "emo_Pride-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6590089797973633, "target_z": 0.8437500035826158, "ce": 6.300607204437256, "genuineness": 4.375550270080566, "identity": 0.838519811630249, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. J'ai posé ton manteau sur la chaise.", "wer": 0.3888888888888889, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/c5429f7e003f5061e4153ecc.mp3" }, { "key": "original-emo_Pride-fr-0-seed1701-scale0.75", "bucket": "emo_Pride", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "a40b79cfedbee153e5eda626b4e13fa3325da98989330a854ba56e491ce49cbf", "task_id": "emo_Pride-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.7280597686767578, "target_z": 0.9765624417824941, "ce": 6.141753673553467, "genuineness": 4.344170093536377, "identity": 0.5406650304794312, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/243450faea546ff9a0bc7834.mp3" }, { "key": "original-emo_Pride-fr-0-seed1701-scale1.0", "bucket": "emo_Pride", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "81027a07d0566e7c266d981690aea51baf449acf6475017750db16129fcc6d5e", "task_id": "emo_Pride-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.5798036456108093, "target_z": 0.6914062907522541, "ce": 6.308549880981445, "genuineness": 4.607763767242432, "identity": 0.7151882648468018, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/08d8086d035f2eb5851ae3db.mp3" }, { "key": "original-emo_Pride-fr-0-seed1702-scale0.0", "bucket": "emo_Pride", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "4d856ea11f72ced625e7c5bebeda2648a6a5c43de10e6fbc85886513c523879b", "task_id": "emo_Pride-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6874416470527649, "target_z": 0.898437457904265, "ce": 6.252951145172119, "genuineness": 4.281409740447998, "identity": 0.7564798593521118, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/24c3281ee673a2ed16590b33.mp3" }, { "key": "original-emo_Pride-fr-0-seed1702-scale0.5", "bucket": "emo_Pride", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "a4a665d323a835f9486437269cef54ca093f138a1fa4c1c4fa86479d48c71815", "task_id": "emo_Pride-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.529030978679657, "target_z": 0.5937500322435417, "ce": 6.086154937744141, "genuineness": 4.18099308013916, "identity": 0.7483149766921997, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/3b158f31a4756a1645456171.mp3" }, { "key": "original-emo_Pride-fr-0-seed1702-scale0.75", "bucket": "emo_Pride", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "1828583d85143ccfbae955bffb56dd9a9d0f56361aa8699658ec502577d2aad7", "task_id": "emo_Pride-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6386998891830444, "target_z": 0.8046874543216492, "ce": 6.09409761428833, "genuineness": 4.231201171875, "identity": 0.6963226795196533, "hypothesis": "La porte est encore ouverte , j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/675d3e897f3af03f72bbf2c5.mp3" }, { "key": "original-emo_Pride-fr-0-seed1702-scale1.0", "bucket": "emo_Pride", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "d4fd410dbaf3cf82aa326bc8b8d26bd3b303281d97a13394ec68a2109b5f5c42", "task_id": "emo_Pride-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6752562522888184, "target_z": 0.875000042991389, "ce": 6.205295085906982, "genuineness": 4.061748504638672, "identity": 0.7851024866104126, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/e547be0b96ae3ceee32d2172.mp3" }, { "key": "original-emo_Pride-fr-1-seed1701-scale0.0", "bucket": "emo_Pride", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "a9e98b0437c98fbbcc21dbfdb6940af2062e09170927507e5b7971bd3aab0e0f", "task_id": "emo_Pride-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0083248615264893, "target_z": 1.5156249337216086, "ce": 6.356205940246582, "genuineness": 4.444586753845215, "identity": 0.7406383156776428, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/8c058bccb32a3007cae51f21.mp3" }, { "key": "original-emo_Pride-fr-1-seed1701-scale0.5", "bucket": "emo_Pride", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "b5c3e36534746faeb363f0428e4be403940da27d732baa4794cd302cd2552b63", "task_id": "emo_Pride-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.7930487990379333, "target_z": 1.101562484773883, "ce": 6.316492557525635, "genuineness": 4.582659721374512, "identity": 0.757027268409729, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/c66f6984d84d5f76bf803bcd.mp3" }, { "key": "original-emo_Pride-fr-1-seed1701-scale0.75", "bucket": "emo_Pride", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "757e04197cc023e0632c3acc340588095bff2cb0ed83dcb3da5948e3e8e64fc3", "task_id": "emo_Pride-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.7219670414924622, "target_z": 0.9648436770042041, "ce": 6.157639026641846, "genuineness": 4.720732688903809, "identity": 0.8190271854400635, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/b250979b9fb842889172ce42.mp3" }, { "key": "original-emo_Pride-fr-1-seed1701-scale1.0", "bucket": "emo_Pride", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "12802886bf5e6dce3caac963ec68c3bbdd82f3324b4b8c2309d602dc5546a8f8", "task_id": "emo_Pride-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6610398888587952, "target_z": 0.8476562585087124, "ce": 6.062326908111572, "genuineness": 4.632867813110352, "identity": 0.7380424737930298, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/99a84d4bb820cd38a7626c9c.mp3" }, { "key": "original-emo_Pride-fr-1-seed1702-scale0.0", "bucket": "emo_Pride", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "11047fa7bd2881cf1c06920f9636e92662a278673f2cc0cade1362e3fddfdc53", "task_id": "emo_Pride-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6590089797973633, "target_z": 0.8437500035826158, "ce": 6.229123115539551, "genuineness": 4.7332844734191895, "identity": 0.6723243594169617, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/9bcffbffd2bbc28a1df1b654.mp3" }, { "key": "original-emo_Pride-fr-1-seed1702-scale0.5", "bucket": "emo_Pride", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "3a7014051899cabeb27dff925aedaaddddc482da44d07b9f977e0636a8bb26f6", "task_id": "emo_Pride-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.5696491003036499, "target_z": 0.6718750161217709, "ce": 6.086154937744141, "genuineness": 4.413206577301025, "identity": 0.7075576186180115, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/3e916cf88448dce06cee16ad.mp3" }, { "key": "original-emo_Pride-fr-1-seed1702-scale0.75", "bucket": "emo_Pride", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "d5e8efa2faeb41c734df3ab7cc8c8c7b7b721fee916f36f20492522f6dfc66e0", "task_id": "emo_Pride-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6955652832984924, "target_z": 0.9140624776086516, "ce": 6.197352409362793, "genuineness": 4.6203155517578125, "identity": 0.758500337600708, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/953dcf7772849b766f5d6d27.mp3" }, { "key": "original-emo_Pride-fr-1-seed1702-scale1.0", "bucket": "emo_Pride", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "c2dc5ff45de756b92da91bff61ede257580a2e375418e16022b90522f1d66699", "task_id": "emo_Pride-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.42850106954574585, "target_z": 0.40039058536731326, "ce": 5.95112943649292, "genuineness": 4.65797233581543, "identity": 0.7323415279388428, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/fr/83bc7e973c7ff216ad88479f.mp3" }, { "key": "original-emo_Pride-nl-0-seed1701-scale0.0", "bucket": "emo_Pride", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "6281517190ea151e115809b9a92384637041ed1e1e8430238602bc2599ba8e08", "task_id": "emo_Pride-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.43357837200164795, "target_z": 0.4101562800044069, "ce": 6.1894097328186035, "genuineness": 4.143336772918701, "identity": 0.668144941329956, "hypothesis": "De deur 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_Pride/nl/3200bccbf77a0518f047d7ac.mp3" }, { "key": "original-emo_Pride-nl-0-seed1701-scale0.5", "bucket": "emo_Pride", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "8033820eac9a542af46e2fc502ba63375252cf9cf395618923a1ecbfc6320f22", "task_id": "emo_Pride-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.3061389625072479, "target_z": 0.16503904134017572, "ce": 6.1894097328186035, "genuineness": 4.118232727050781, "identity": 0.7770538330078125, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/73e3938208eab477c5e03a04.mp3" }, { "key": "original-emo_Pride-nl-0-seed1701-scale0.75", "bucket": "emo_Pride", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "c72a4c8b838cc7faa129070cbf73074de882600636f9e476b394c4faf5360291", "task_id": "emo_Pride-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.6041744947433472, "target_z": 0.7382812352217101, "ce": 6.149696350097656, "genuineness": 4.143336772918701, "identity": 0.5559380054473877, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/0e0c9b8be30f77dca11de31f.mp3" }, { "key": "original-emo_Pride-nl-0-seed1701-scale1.0", "bucket": "emo_Pride", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "aac70f9643460467b9c6d773f5e49d695cc289542b1a7b8fd3f663408be65dd3", "task_id": "emo_Pride-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.3102007806301117, "target_z": 0.17285155119236903, "ce": 6.165581703186035, "genuineness": 4.306513786315918, "identity": 0.29199254512786865, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/72aa8a35703460228b41d2cc.mp3" }, { "key": "original-emo_Pride-nl-0-seed1702-scale0.0", "bucket": "emo_Pride", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "85bd6e1bb860ab8615fc5a1225eb93ba204fb43a1671d400b960b4478c3daad4", "task_id": "emo_Pride-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.3381257653236389, "target_z": 0.22656252776527205, "ce": 6.070269584655762, "genuineness": 4.293961524963379, "identity": 0.7033904194831848, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/fbe7f62a4c597d6a4cdcbc48.mp3" }, { "key": "original-emo_Pride-nl-0-seed1702-scale0.5", "bucket": "emo_Pride", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "226eed414fa7868d5a6e20b829f1db5ac41ddf89098253df83f649115207c5f9", "task_id": "emo_Pride-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.4386556148529053, "target_z": 0.4199218599977965, "ce": 6.062326908111572, "genuineness": 4.394378662109375, "identity": 0.6171609163284302, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/6ef3473c281000df348f93cb.mp3" }, { "key": "original-emo_Pride-nl-0-seed1702-scale0.75", "bucket": "emo_Pride", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "0684f353e6c90360661eec7af4587365d1d82faa7d25500cba8930e3006e0837", "task_id": "emo_Pride-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.18631549179553986, "target_z": -0.06542968402934099, "ce": 6.0146708488464355, "genuineness": 4.582659721374512, "identity": 0.5520496368408203, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/e8f83e00eabf56713e01af27.mp3" }, { "key": "original-emo_Pride-nl-0-seed1702-scale1.0", "bucket": "emo_Pride", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "9d8830d222a8acc3ac69b7044ab3f14f62fdd519172cc1f796a84b7f2a4c50e8", "task_id": "emo_Pride-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.24216541647911072, "target_z": 0.04199218313368706, "ce": 5.95112943649292, "genuineness": 4.281409740447998, "identity": 0.5404736995697021, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/ae0a4fccb45fa33da2fc6993.mp3" }, { "key": "original-emo_Pride-nl-1-seed1701-scale0.0", "bucket": "emo_Pride", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "08fbe0e92944e7a068bd15a89e5856b82b09024993dcbe65fbda553e97224b01", "task_id": "emo_Pride-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.5554327368736267, "target_z": 0.6445312316390943, "ce": 6.260893821716309, "genuineness": 4.193545341491699, "identity": 0.7523945569992065, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/24ed1268b9033e766079f42f.mp3" }, { "key": "original-emo_Pride-nl-1-seed1701-scale0.5", "bucket": "emo_Pride", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "f88f31e1a557f74d2be80a93ac2c287364563d14dc0ae5abca8949eb9709dc74", "task_id": "emo_Pride-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.24470405280590057, "target_z": 0.04687500179130787, "ce": 6.173524379730225, "genuineness": 4.425758361816406, "identity": 0.6317481994628906, "hypothesis": "Ik 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_Pride/nl/45fbcdfd8157c1cde5aeba59.mp3" }, { "key": "original-emo_Pride-nl-1-seed1701-scale0.75", "bucket": "emo_Pride", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "a244a6fdf349e17ccb155484beea1ff33439b23783b15ea7c405426e10ea6140", "task_id": "emo_Pride-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.42850106954574585, "target_z": 0.40039058536731326, "ce": 6.213237762451172, "genuineness": 4.394378662109375, "identity": 0.7150070667266846, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/151659b3b0c31eb4ef3ed02b.mp3" }, { "key": "original-emo_Pride-nl-1-seed1701-scale1.0", "bucket": "emo_Pride", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "eea9ccccf4c024e607cd65f0e242bd022c1de8c33fc37dce94abcbc3dca97337", "task_id": "emo_Pride-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.4376401901245117, "target_z": 0.41796878985660024, "ce": 6.125868320465088, "genuineness": 4.143336772918701, "identity": 0.748668909072876, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/03d9331258dfaad1775ae4db.mp3" }, { "key": "original-emo_Pride-nl-1-seed1702-scale0.0", "bucket": "emo_Pride", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "957abd07844fceb52349c41910bf3b26b423ec9e3402310d0c9cb9d97233482f", "task_id": "emo_Pride-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.212209552526474, "target_z": -0.015624991043460625, "ce": 6.157639026641846, "genuineness": 4.444586753845215, "identity": 0.6838680505752563, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/2c17ceb1a2c4762abd138289.mp3" }, { "key": "original-emo_Pride-nl-1-seed1702-scale0.5", "bucket": "emo_Pride", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "a65378ab4b9b8fe5305bce9499eaf6a763281c9ae6a855057d45bd29680a1283", "task_id": "emo_Pride-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.3259403109550476, "target_z": 0.20312499820869212, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.6027362942695618, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/1b57c7a2564d2ba35e5c28b2.mp3" }, { "key": "original-emo_Pride-nl-1-seed1702-scale0.75", "bucket": "emo_Pride", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "7a99f3a1520add6e8c421d48991aa01e986474cb3d11249ede37b130835ab5a9", "task_id": "emo_Pride-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.3848366141319275, "target_z": 0.31640627642179114, "ce": 6.197352409362793, "genuineness": 4.168440818786621, "identity": 0.6101366281509399, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/6cc2db7ef4c65043b28c717e.mp3" }, { "key": "original-emo_Pride-nl-1-seed1702-scale1.0", "bucket": "emo_Pride", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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 Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "cb96d1fe8a8697c2a00102ad7fddfa460f3b581353e651ee5e8065bf5f6964ad", "mp3_sha256": "68e59f42c30c1b3b1f362746642b873ae85c97025f2884de84c8caf336e829d9", "task_id": "emo_Pride-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pride. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pride. 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 Pride. 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 Pride. 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": 0.30360034108161926, "target_z": 0.1601562513434809, "ce": 6.070269584655762, "genuineness": 4.331617832183838, "identity": 0.5313975214958191, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pride/nl/59ad82900d4fdefc57a39355.mp3" } ], "source_standard_audio_unchanged": true }