{ "complete": true, "report": { "bucket": "emo_Longing", "label": "Intense Longing", "definition": { "id": "emo_Longing", "category": "emotion", "head": "emo_Longing", "pole": "high", "label": "Intense Longing", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_longing/full-v2-sealed/sealed-selected", "mission": "emotion_longing", "format_status": "CANONICAL", "heldout": true, "qualified": true, "source_cfg": 2.5, "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": 6.297350635528565, "genuineness": 4.56376868724823, "wer": 0.0122387761408896, "identity": 0.6264193868637085, "voiceclap": 0.06624035626649856, "fitness": 0.7948030696145252, "steering_v2": 0.9143916627417668, "raw_target": 1.4928108739852906, "target_cdf": 0.9143916627417668, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.300289430618286, "genuineness": 4.584542388916016, "wer": 0.012366108043527398, "identity": 0.6264193868637085, "fitness": 0.7957429781446134, "steering_v2": 0.9146337437050621 }, "none": { "n": 50, "ce": 6.294411840438843, "genuineness": 4.542994985580444, "wer": 0.012111444238251803, "identity": null, "fitness": 0.793863161084437, "steering_v2": 0.9141495817784715 } } } } ], "selected_wording": { "id": "manual-bd19fff54e5e", "general": "Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.", "inline": [ "Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.", "Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.", "Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance." ], "cfg": 2.5, "recipe": "P06", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-2.5", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 1.4684570217841637, "target_raw": 1.3687865793704987, "ce": 5.730323314666748, "genuineness": 4.490715599060058, "identity": 0.5383007764816284, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.025570313911885023, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 1.5466796825565265, "target_raw": 1.418522971868515, "ce": 5.660626363754273, "genuineness": 4.470318460464478, "identity": 0.5132293835282326, "wer": 0.005718954248366013, "valid_fraction": 1, "identity_delta": 0.0004989209584891797, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 1.4684570217841637, "target_raw": 1.3687865793704987, "ce": 5.730323314666748, "genuineness": 4.490715599060058, "identity": 0.5383007764816284, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.025570313911885023, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 1.4135742140079273, "target_raw": 1.333890388906002, "ce": 5.758619070053101, "genuineness": 4.482556676864624, "identity": 0.5488786660134792, "wer": 0.011458333333333333, "valid_fraction": 1, "identity_delta": 0.03614820344373584, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 1.286132825353031, "target_raw": 1.252859203517437, "ce": 5.922138833999634, "genuineness": 4.512054133415222, "identity": 0.5325463727116585, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.019815910141915083, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 0.8458495961649403, "target_raw": 0.9729134783148765, "ce": 6.017053747177124, "genuineness": 4.529627096652985, "identity": 0.5624115392565727, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.04968107668682933, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 0.8141113210118909, "target_raw": 0.9527332991361618, "ce": 6.191395354270935, "genuineness": 4.534020304679871, "identity": 0.6232313945889473, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.1105009320192039, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 0.778100577043825, "target_raw": 0.9298365518450737, "ce": 6.0736452579498295, "genuineness": 4.477535927295685, "identity": 0.5978550776839257, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.08512461511418223, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 0.41110840063917664, "target_raw": 0.6964915499091149, "ce": 6.196955251693725, "genuineness": 4.518957805633545, "identity": 0.5639419741928577, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.051211511623114346, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 0.30549318306283196, "target_raw": 0.6293381206691265, "ce": 6.20172085762024, "genuineness": 4.497619223594666, "identity": 0.5864015072584152, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.07367104468867183, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 1.5466796825565265, "target_raw": 1.418522971868515, "ce": 5.660626363754273, "genuineness": 4.470318460464478, "identity": 0.5132293835282326, "wer": 0.005718954248366013, "valid_fraction": 1, "identity_delta": 0.0004989209584891797, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 1.5441406137947935, "target_raw": 1.4169085532426835, "ce": 5.785723400115967, "genuineness": 4.505150485038757, "identity": 0.5693844631314278, "wer": 0.005718954248366013, "valid_fraction": 1, "identity_delta": 0.05665400056168437, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 1.5026855233019552, "target_raw": 1.390550121665001, "ce": 5.639330124855041, "genuineness": 4.459649229049683, "identity": 0.514834639430046, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.002104176860302687, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 1.4792968747802901, "target_raw": 1.3756788939237594, "ce": 5.8540303945541385, "genuineness": 4.51707501411438, "identity": 0.5440096944570542, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.03127923188731074, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 1.467651383542158, "target_raw": 1.3682743296027184, "ce": 5.911217617988586, "genuineness": 4.50734703540802, "identity": 0.5794511437416077, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.06672068117186428, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 1.450683559200613, "target_raw": 1.3574856609106063, "ce": 5.614956045150757, "genuineness": 4.40316481590271, "identity": 0.5104306459426879, "wer": 0.005718954248366013, "valid_fraction": 1, "identity_delta": -0.0022998166270554064, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 1.4063720708388883, "target_raw": 1.329311043024063, "ce": 5.7055521488189695, "genuineness": 4.452745509147644, "identity": 0.5317855849862099, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.019055122416466473, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 1.2629883185091428, "target_raw": 1.2381432086229325, "ce": 5.980120301246643, "genuineness": 4.516447401046753, "identity": 0.5374329820275306, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.024702519457787276, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 1.2092773263379877, "target_raw": 1.2039920948445797, "ce": 5.838740706443787, "genuineness": 4.47251513004303, "identity": 0.5562241673469543, "wer": 0.005718954248366013, "valid_fraction": 1, "identity_delta": 0.04349370477721095, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 1.2039550986953425, "target_raw": 1.2006080575287341, "ce": 5.910621953010559, "genuineness": 4.4813015222549435, "identity": 0.6015885720029474, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.08885810943320394, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 1.1686279373636157, "target_raw": 1.1781459532678127, "ce": 6.031350493431091, "genuineness": 4.502012443542481, "identity": 0.5409683510661125, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.028237888496369122, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 1.0520508018111878, "target_raw": 1.1040225967764854, "ce": 5.992431497573852, "genuineness": 4.469690871238709, "identity": 0.5766085736453533, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.06387811107560992, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 0.9178711005060805, "target_raw": 1.0187069833278657, "ce": 6.079800844192505, "genuineness": 4.514564514160156, "identity": 0.5684001117944717, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.05566964922472835, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 0.8954101540345916, "target_raw": 1.0044256173074246, "ce": 6.102636003494263, "genuineness": 4.559438228607178, "identity": 0.580990320444107, "wer": 0.0061111111111111106, "valid_fraction": 1, "identity_delta": 0.06825985787436366, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 0.8344482419174398, "target_raw": 0.9656641438603402, "ce": 6.028372025489807, "genuineness": 4.497932982444763, "identity": 0.5681707754731178, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.055440312903374436, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 0.7541259931826411, "target_raw": 0.914592768251896, "ce": 6.092310523986816, "genuineness": 4.539982581138611, "identity": 0.6047381147742271, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.09200765220448374, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 0.6590576140612108, "target_raw": 0.8541453458368778, "ce": 6.156050491333008, "genuineness": 4.480046343803406, "identity": 0.5915269210934639, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": 0.0787964585237205, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 0.6422607545141428, "target_raw": 0.843465381860733, "ce": 6.161213207244873, "genuineness": 4.530568408966064, "identity": 0.5875803954899311, "wer": 0.009444444444444445, "valid_fraction": 1, "identity_delta": 0.07484993292018771, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 0.5462402298801009, "target_raw": 0.7824125558137893, "ce": 6.158830356597901, "genuineness": 4.465925216674805, "identity": 0.5653142362833024, "wer": 0.0061111111111111106, "valid_fraction": 1, "identity_delta": 0.052583773713558914, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 0.522387700452797, "target_raw": 0.7672463782131672, "ce": 6.144533634185791, "genuineness": 4.415403151512146, "identity": 0.5774082995951175, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.06467783702537418, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 0.4222412213050625, "target_raw": 0.7035701423883438, "ce": 6.12269127368927, "genuineness": 4.427955245971679, "identity": 0.5869445830583573, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.07421412048861384, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 0.39177244186393145, "target_raw": 0.6841971479356289, "ce": 6.16955304145813, "genuineness": 4.4605906248092655, "identity": 0.540298780798912, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.027568318229168654, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 0.3601074221038645, "target_raw": 0.6640635468065739, "ce": 6.13480384349823, "genuineness": 4.465611433982849, "identity": 0.5512137614190579, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.03848329884931445, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 0.3335693283620846, "target_raw": 0.6471898041665554, "ce": 6.173127269744873, "genuineness": 4.456197416782379, "identity": 0.5880515158176423, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.07532105324789881, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.05743408889489676, "target_raw": 0.39857771098613737, "ce": 6.188615417480468, "genuineness": 4.387474751472473, "identity": 0.5127304625697434, "wer": 0.002631578947368421, "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": -0.08764649438095655, "target_raw": 0.3793677270412445, "ce": 6.189012575149536, "genuineness": 4.343228650093079, "identity": 0.562597033381462, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.049866570811718705, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": 0.10822753118498343, "target_raw": 0.5039105042815208, "ce": 6.210060691833496, "genuineness": 4.382767713069915, "identity": 0.5373779989778995, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.024647536408156156, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.04873046561913345, "target_raw": 0.4041117444634438, "ce": 6.190601086616516, "genuineness": 4.300551581382751, "identity": 0.5498326897621155, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.037102227192372085, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.22144531263914963, "target_raw": 0.29429429084062575, "ce": 6.257081289291381, "genuineness": 4.369650764465332, "identity": 0.5816589125990868, "wer": 0.01524334551794506, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 1.199921884037402, "target_raw": 1.1980436146259308, "ce": 5.812966804504395, "genuineness": 4.489021053314209, "identity": 0.5362272065877914, "wer": 0.010424480172763925, "valid_fraction": 1, "identity_delta": -0.04543170601129532, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 1.1383007706416721, "target_raw": 1.1588630005717278, "ce": 5.728695058822632, "genuineness": 4.451992473602295, "identity": 0.5308062396198511, "wer": 0.02199513110840342, "valid_fraction": 1, "identity_delta": -0.05085267297923565, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 1.199921884037402, "target_raw": 1.1980436146259308, "ce": 5.812966804504395, "genuineness": 4.489021053314209, "identity": 0.5362272065877914, "wer": 0.010424480172763925, "valid_fraction": 1, "identity_delta": -0.04543170601129532, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": -0.06162111339572986, "ci95_z": [ -0.19261720909748642, 0.05173823953074554 ], "language_deltas": { "en": 0.11562490801477468, "de": 0.03359382924204925, "fr": -0.29199214828177694, "nl": -0.12177735563264556, "es": -0.04355480032105069 }, "languages_improved": 2, "clear_gain": false, "delta_ce": -0.0842717456817627, "delta_genuineness": -0.03702857971191406, "delta_wer": 0.011570650935639495, "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": -0.06162111339572986, "ci95_z": [ -0.19261720909748642, 0.05173823953074554 ], "language_deltas": { "en": 0.11562490801477468, "de": 0.03359382924204925, "fr": -0.29199214828177694, "nl": -0.12177735563264556, "es": -0.04355480032105069 }, "languages_improved": 2, "clear_gain": false, "delta_ce": -0.0842717456817627, "delta_genuineness": -0.03702857971191406, "delta_wer": 0.011570650935639495, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 1.4213671966765515, "ci95_z": [ 1.2413281213528151, 1.6404297010707503 ], "language_deltas": { "en": 1.3093750498009182, "de": 1.2777343305453568, "fr": 1.5610351452461941, "nl": 1.1708984479362219, "es": 1.7877930098540666 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.4441144847869873, "delta_genuineness": 0.11937028884887696, "delta_wer": -0.004818865345181135, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 5.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793024873.7404544, "example": { "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "sentences": [ "Escribí el número en el sobre.", "Léelo bien... y comprueba las dos últimas cifras.", "Llámame cuando tengas un momento." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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.", "language": "es", "seed": 1702, "scale": 0.0, "cfg": 5.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "005d6576be006069c5081051ff2c5a8f214e01aaac3a1d9c41ad208d2eccfcc9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4a934bd490286b03b75115b788b07cba40c6cba82500f90e11b5a73408a49bc", "generation_seconds_batch": 24.24957196705509, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.53289794921875, "target_z": 1.7265623520619784, "ce": 5.172747611999512, "genuineness": 4.243753433227539, "identity": 0.44958388805389404, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/005d6576be006069c5081051ff2c5a8f214e01aaac3a1d9c41ad208d2eccfcc9.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "0060259a73e855313c15ac28bf11c79a0c8da3d1e2d2fc53bbe3bb22524b916d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cf48f11e671693078fdef1f89cc68d7e7c0cf8d7b072df1a7b3974fd086aa890", "generation_seconds_batch": 29.152986978995614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8548438549041748, "target_z": 0.660156190678318, "ce": 5.824047088623047, "genuineness": 4.595211505889893, "identity": 0.7328850030899048, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0060259a73e855313c15ac28bf11c79a0c8da3d1e2d2fc53bbe3bb22524b916d.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": "0078ec9b7ce32283287daeae95c8602db6880186707371ea295d7a1e8dcb9af2", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7d5b157f1c61f5994eb4a04497aa2368e462785c514b102de9054cb620cb62b", "generation_seconds_batch": 24.23090143292211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0048038959503174, "target_z": 2.468750052730384, "ce": 5.808161735534668, "genuineness": 4.582659721374512, "identity": 0.4836510419845581, "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_Longing/0078ec9b7ce32283287daeae95c8602db6880186707371ea295d7a1e8dcb9af2.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "00c46c2a53e6770ee3c21762a1d160006d91bfcc36ce1d0d4575a70d7411d257", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "14b7f8fc586ccd4eb84e3cb8c757f74be19e956e61eb090fe9e82c31da0ace0e", "generation_seconds_batch": 21.484699035063386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35810092091560364, "target_z": -0.121093756591298, "ce": 5.998785495758057, "genuineness": 4.425758361816406, "identity": 0.6737900972366333, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/00c46c2a53e6770ee3c21762a1d160006d91bfcc36ce1d0d4575a70d7411d257.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": "0142f9211a93f9ccd27f6ddf4ced9b6f6829bf42fd5fb14b0b3d252ef43edfe8", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "596552ca687c8cadf10f05b26587c39b708791adfe26dcafdbd797376887d159", "generation_seconds_batch": 28.206361901015043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.036155104637146, "target_z": 0.9453125454067195, "ce": 5.665193557739258, "genuineness": 4.65797233581543, "identity": 0.7338740229606628, "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_Longing/0142f9211a93f9ccd27f6ddf4ced9b6f6829bf42fd5fb14b0b3d252ef43edfe8.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "015c78aecfb210173ecee4b044d07686784a75024ab2b508d268fb2044fb6aba", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c615472ee4b03ecffc5e028243c084a36bb08e4ac9c0c4c2b8e17d79d76f9b06", "generation_seconds_batch": 25.98875965597108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6223118305206299, "target_z": 1.8671875834897746, "ce": 6.348263263702393, "genuineness": 4.545003414154053, "identity": 0.3651111125946045, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/015c78aecfb210173ecee4b044d07686784a75024ab2b508d268fb2044fb6aba.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "745fae62ff28b7b05e656de24f9d97c6c2c16232b1aa8a8d8ed25432928eb9c2", "generation_seconds_batch": 21.630562967038713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016940027475357056, "target_z": -0.7109375190415276, "ce": 6.054384231567383, "genuineness": 4.231201171875, "identity": 0.7964902520179749, "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_Longing/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "02a06e505077054138352a380947469930cf8567429d5bc6ad9c9e570205f631", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f653b5bb192a830aa7afe82aeb9a9a84dffb779d99e143366dfa23ae20773b04", "generation_seconds_batch": 23.27804314706009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3987774848937988, "target_z": 1.5156250673777127, "ce": 5.673136234283447, "genuineness": 4.482243061065674, "identity": 0.4889528155326843, "hypothesis": "Encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/02a06e505077054138352a380947469930cf8567429d5bc6ad9c9e570205f631.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "02abf886f9b935f68c58ab46722e90c6a8537b3ccad784711e3444e606e4132c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "61ce455546b3104f26d8f9e3bed02c04d81b455b421d70fa48f6bb4aca51e9df", "generation_seconds_batch": 25.39416087407153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2646567821502686, "target_z": 1.304687407721828, "ce": 5.831989288330078, "genuineness": 4.406930446624756, "identity": 0.49129027128219604, "hypothesis": "The 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_Longing/02abf886f9b935f68c58ab46722e90c6a8537b3ccad784711e3444e606e4132c.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "0338c36ad391e699595822afc95bd6690c5b147bc8598bb4edef7965c5d2c843", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "052bd9c7b0b9d13f0d00f553cf519683ff22ea56722bf50e9352672e706a9670", "generation_seconds_batch": 18.36334352393169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36431020498275757, "target_z": -0.11132813635167989, "ce": 6.308549880981445, "genuineness": 4.65797233581543, "identity": 0.6466547250747681, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0338c36ad391e699595822afc95bd6690c5b147bc8598bb4edef7965c5d2c843.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "0360c94777c01427c65f38029ed15f3f30afa4b96cdbac27c677d0c4059004fd", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1da40819883569a85de852c7a99852878a5bda1a83463161220af1cff5cdff3f", "generation_seconds_batch": 22.429101904970594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8076533079147339, "target_z": 0.5859374956058013, "ce": 6.149696350097656, "genuineness": 4.8588056564331055, "identity": 0.5567549467086792, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0360c94777c01427c65f38029ed15f3f30afa4b96cdbac27c677d0c4059004fd.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "03cf60c409b7cccd51727ecd332da0df5738d4ad32adcf370f790f70a329cda5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a83bd46904c3d07cb5066cf00a1f66e54e6f5ea8e3f7812ce0084189527698c6", "generation_seconds_batch": 22.43135752598755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5080609321594238, "target_z": 1.6875000585893156, "ce": 5.148920059204102, "genuineness": 4.068024158477783, "identity": 0.3440791964530945, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/03cf60c409b7cccd51727ecd332da0df5738d4ad32adcf370f790f70a329cda5.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "03e6074cee5edc369961d84cc6f085cf81115e3d0f852b30eea30930a3d360c3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "054049175f6947073b8fd14107b505d5eb0d6a81a6e1b3a63ec916899751364b", "generation_seconds_batch": 24.4326223769458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0898597240447998, "target_z": -0.5429687478029007, "ce": 5.998785495758057, "genuineness": 4.381826400756836, "identity": 0.2887307107448578, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/03e6074cee5edc369961d84cc6f085cf81115e3d0f852b30eea30930a3d360c3.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "048eea6e2e5ae8dc9f3eeb589edeca67b0011f7536dca07d1d61ada9190b863d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "74c550b63a69b3175edd9080948f65a9905496bed444dde608f06bbab1920d44", "generation_seconds_batch": 24.8236044900259, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.756432294845581, "target_z": 2.07812486817404, "ce": 6.133810997009277, "genuineness": 4.909013748168945, "identity": 0.711837649345398, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/048eea6e2e5ae8dc9f3eeb589edeca67b0011f7536dca07d1d61ada9190b863d.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "04ba5c2fbb425f82562f01fd8fdf54bc4c091222a442b20d68c2b33e8eea9a9b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "54599cf3ab78bed5419b480cf3f42fbc4c0c5547aeec34080d237d71656f4432", "generation_seconds_batch": 19.186337475082837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5300981998443604, "target_z": 0.1494140974704977, "ce": 5.792276382446289, "genuineness": 4.65797233581543, "identity": 0.725136399269104, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/04ba5c2fbb425f82562f01fd8fdf54bc4c091222a442b20d68c2b33e8eea9a9b.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "5f4e29ef9d9d59edf1f041e02b8274fa9f469a419117f9c70ebb8fafcd2236ec", "generation_seconds_batch": 19.355546964914538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8225556015968323, "target_z": 0.6093750029294658, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.6411917805671692, "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_Longing/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "05bb9f7a716a9c4b14aaf67144513fe5dba905f0713f59adc49fb2dea87168a1", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6cdad9b00046e7b0ed2bc9cc2a54c017f0ed4d65623409f2d014be64c5df475f", "generation_seconds_batch": 20.31204782309942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.163761615753174, "target_z": 2.7187500058589316, "ce": 5.311744689941406, "genuineness": 4.394378662109375, "identity": 0.3246111273765564, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/05bb9f7a716a9c4b14aaf67144513fe5dba905f0713f59adc49fb2dea87168a1.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "0612c883e33d28f04fa451e9a6a118486f308cff6510a69319c06d87654047cf", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "66505ff696e2ff78c9b536924d04da2ecfbf2925b6452d934c41dff9cbb85207", "generation_seconds_batch": 29.05902374209836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7405930161476135, "target_z": 0.4804687595207638, "ce": 6.117925643920898, "genuineness": 4.65797233581543, "identity": 0.4103558361530304, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0612c883e33d28f04fa451e9a6a118486f308cff6510a69319c06d87654047cf.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "0633983d70a8cb9ec7026c26de2ccfe25742add453ca0056269bb2ad0571d835", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bbea55b059fbe71e934a636c130e2d9344c5a5a2af55f116acb621f976cb019c", "generation_seconds_batch": 17.040210095932707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20162689685821533, "target_z": -0.36718748974686977, "ce": 6.24500846862793, "genuineness": 4.419482707977295, "identity": 0.5388792753219604, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0633983d70a8cb9ec7026c26de2ccfe25742add453ca0056269bb2ad0571d835.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "0635d0efa7a2b7aa7e3f59c852960450bdfa920731dbf255045ec0293efc2e4e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "16ce9e668c29ba64a08177cb314d06fc32362ef3b4dfb3f52bd9334a04cef646", "generation_seconds_batch": 18.239294886006974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.408712387084961, "target_z": 1.5312501347554257, "ce": 6.300607204437256, "genuineness": 4.6956281661987305, "identity": 0.3276246190071106, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0635d0efa7a2b7aa7e3f59c852960450bdfa920731dbf255045ec0293efc2e4e.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "06bbd2127f12b0ef523f7e3a9d9bbf40b6d5ba037acfa263d25e0dc9061aba3b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1e37103d4d5f36a70b0a3ddc89b6643aa07ff4ede92f1ff217a0b8fa3084b79", "generation_seconds_batch": 22.412062837043777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1802105903625488, "target_z": 1.1718750849545074, "ce": 6.3641486167907715, "genuineness": 4.595211505889893, "identity": 0.7734378576278687, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/06bbd2127f12b0ef523f7e3a9d9bbf40b6d5ba037acfa263d25e0dc9061aba3b.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": "06f993167645cd841017cfed5681c60ea481b4aaaa92bc157a7d21fc6b4349d6", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c111d6162443cefa45de6be191214f9666887515a8a2499fb397273319d33070", "generation_seconds_batch": 16.42294567602221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.433549404144287, "target_z": 1.5703124282280885, "ce": 5.855817794799805, "genuineness": 4.432034492492676, "identity": 0.582929253578186, "hypothesis": "Escribí el número en el sobre, léelilo 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_Longing/06f993167645cd841017cfed5681c60ea481b4aaaa92bc157a7d21fc6b4349d6.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": "071b9fafa50913b8d5a78738a6826bf03c458052e2e7f7f0c5e38b9f88a5ae41", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e4ab31e0b2630cc14aae52c1eb6470e140fbdacb217fa56980cdc4d6bd47534d", "generation_seconds_batch": 16.62595081795007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0287039279937744, "target_z": 0.9335937448734349, "ce": 5.665193557739258, "genuineness": 4.632867813110352, "identity": 0.8202794790267944, "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_Longing/071b9fafa50913b8d5a78738a6826bf03c458052e2e7f7f0c5e38b9f88a5ae41.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "0755ff4dc3f29e086c329aa67bc4ed4eb6e62bfe34eb7acd42efc11e5f948fb7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9b265b8e31f43abc6645a5ca7e8e6a569ddddea0539054a968b0154c7a2f751b", "generation_seconds_batch": 24.515410411986522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5974745750427246, "target_z": 1.8281249150454926, "ce": 5.855817794799805, "genuineness": 4.369274139404297, "identity": 0.7975608706474304, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0755ff4dc3f29e086c329aa67bc4ed4eb6e62bfe34eb7acd42efc11e5f948fb7.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": "07bed7f6c8a1b5179d8e6226401c2fbb3351e233515b904848930c1841c7a7c3", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7f43b5dada41c15446bdb16a8b538bbd0c544aa6f91f972da8f26d34f210613c", "generation_seconds_batch": 18.51978092396166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7961719036102295, "target_z": 2.1406251376848915, "ce": 5.685050010681152, "genuineness": 4.7332844734191895, "identity": 0.7472569346427917, "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_Longing/07bed7f6c8a1b5179d8e6226401c2fbb3351e233515b904848930c1841c7a7c3.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "0891b76b6dd6ad458351ad4b47742c6b31bbc26db086872420e33aef5619b75e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b6ea1287a7c87cd2cd8ae08a10238cd8bb9ab80bf078894b3177bd90505f5e62", "generation_seconds_batch": 26.844304302940145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7356256246566772, "target_z": 0.4726563195748122, "ce": 5.4666266441345215, "genuineness": 4.607763767242432, "identity": 0.5053920149803162, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0891b76b6dd6ad458351ad4b47742c6b31bbc26db086872420e33aef5619b75e.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "08932fea8b88a12d944ae7be0992705833e6588880f28660b3ed1bd167db872e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "eca3d0027677f4c28c495a2b2125e786678c39950c01d88c4f0cd4c45fee397c", "generation_seconds_batch": 32.740283814957365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4239193797111511, "target_z": -0.017578107057022122, "ce": 6.221180438995361, "genuineness": 4.607763767242432, "identity": 0.5515114665031433, "hypothesis": "Die Tür 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_Longing/08932fea8b88a12d944ae7be0992705833e6588880f28660b3ed1bd167db872e.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "089861b20919bac213f7a76251613000324fd70370b66d881d15920090e27515", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "17d1336c0a1fad386850416d364a45b1f1244ed45b8b8dc26490dddf816f2297", "generation_seconds_batch": 19.080621612956747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9442576169967651, "target_z": 0.8007812346203047, "ce": 6.0305562019348145, "genuineness": 4.557555198669434, "identity": 0.8193281888961792, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/089861b20919bac213f7a76251613000324fd70370b66d881d15920090e27515.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "09352831f8c58ff1c63ec4099265a380109796555f52c519c4061e017649fd49", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "06a39de2f157388688b18c064af770bd7c8a9f52828a13d6372b75481ae0bb5c", "generation_seconds_batch": 24.274772215052508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6223118305206299, "target_z": 1.8671875834897746, "ce": 5.816103935241699, "genuineness": 4.68307638168335, "identity": 0.5542740225791931, "hypothesis": "Encontrado. La cajita estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/09352831f8c58ff1c63ec4099265a380109796555f52c519c4061e017649fd49.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "09e65ac252b442bef34938c1c58369e763873611b48efa6bd616521437d8a749", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0c63fd0f9223ca750e8a2a653ec5b43f37952ce6b3434526477bacb7383f31c7", "generation_seconds_batch": 21.903917885036208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2944614887237549, "target_z": 1.3515626098549667, "ce": 5.804190158843994, "genuineness": 4.7834930419921875, "identity": 0.5428838729858398, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/09e65ac252b442bef34938c1c58369e763873611b48efa6bd616521437d8a749.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "0a3080c2ef2a8d3e4b0ee803b85d2bf3799ef1a8006b4a9fc1a601e3c13527b1", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2f0d2ee055c3cfcc61a364a1be6ca98684fb7662cf01ac5ec7ccdcae84ff2829", "generation_seconds_batch": 16.77577744598966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4136797189712524, "target_z": 1.5390624809584725, "ce": 5.736677646636963, "genuineness": 4.7332844734191895, "identity": 0.5750885009765625, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0a3080c2ef2a8d3e4b0ee803b85d2bf3799ef1a8006b4a9fc1a601e3c13527b1.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "0b24fa3b97607d0a39bd1745220d4ae30f14506ceb571210818793b46572cbf0", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "05a98233ffe8c17449654bfcfc67b04b86f14ccc7d74cd0172029f3637cbf852", "generation_seconds_batch": 29.152986978995614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7828161716461182, "target_z": 0.5468750146473289, "ce": 5.673136234283447, "genuineness": 4.507347106933594, "identity": 0.6313031911849976, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0b24fa3b97607d0a39bd1745220d4ae30f14506ceb571210818793b46572cbf0.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "0ba5142096b9e06b2f7ce806aed7d5556453719c76267d13c52348aab02b886f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4beab46211fd7b3f15a090e853e803577aec3902026c83091c4f10732f28b06f", "generation_seconds_batch": 18.026870685978793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9194204807281494, "target_z": 0.7617187536618322, "ce": 5.8875885009765625, "genuineness": 4.532451152801514, "identity": 0.4351431727409363, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0ba5142096b9e06b2f7ce806aed7d5556453719c76267d13c52348aab02b886f.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "0bfcd307e32296be68219275cec7fc49a7fdef1a4db5923bcaac7791d14c7ef6", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "eeb78884503db581f54a7edcfeb36bdd8ea5f698a758be0b2d1ba25351e6c434", "generation_seconds_batch": 21.977943881996907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9253249168395996, "target_z": 2.3437498886803003, "ce": 5.967014789581299, "genuineness": 4.2249250411987305, "identity": 0.5614638328552246, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0bfcd307e32296be68219275cec7fc49a7fdef1a4db5923bcaac7791d14c7ef6.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "0c74aab57f6f7cb3c463d14b160de29f3a5e205f4e7990357f9254ada5eb90d4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c24d98fa35fe3b630cd5e0287ff968887f400d0c7dc8d5a026117a776341a47f", "generation_seconds_batch": 18.508316360996105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4981260299682617, "target_z": 1.6718749912116027, "ce": 6.181467056274414, "genuineness": 4.344170093536377, "identity": 0.459898978471756, "hypothesis": "The 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_Longing/0c74aab57f6f7cb3c463d14b160de29f3a5e205f4e7990357f9254ada5eb90d4.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "0caade678e30bfc851399b76480bf39ab0356851573fe186000dce9757fe7730", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "30898f515bce89367d2509fc441dc0096dcca6681daff82a29b04f18a97ce79c", "generation_seconds_batch": 24.051298122038133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.094217538833618, "target_z": 2.609374909186561, "ce": 6.23706579208374, "genuineness": 4.8588056564331055, "identity": 0.7607954144477844, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0caade678e30bfc851399b76480bf39ab0356851573fe186000dce9757fe7730.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "3156261d58ffa10d61ea04efa14c78fc766f6c60676c91f1238b5c9d26ee95d5", "generation_seconds_batch": 18.696252972004004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010380834341049194, "target_z": -0.6679687712386269, "ce": 5.911416053771973, "genuineness": 4.074300289154053, "identity": 0.4875211715698242, "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_Longing/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "0cc6176935c54a0bc57aca36cff9cada79e2a314a4cbaac0043c0acb7db4de7c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d0cc679d16e3e221a7052d344bed6095dad5257580278d57f177d6d7012a06a0", "generation_seconds_batch": 22.154107308015227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.09576416015625, "target_z": 1.0390623872155675, "ce": 6.09409761428833, "genuineness": 4.532451152801514, "identity": 0.7343519330024719, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0cc6176935c54a0bc57aca36cff9cada79e2a314a4cbaac0043c0acb7db4de7c.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "0d1b1573d32b8fce463207bb0d98802a0b7239deb33721fe8942d7766943e1e6", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f61727060664f140d7520101633d91b65b2500899caeb1a884aca6ed8915dd77", "generation_seconds_batch": 22.894997863913886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17554789781570435, "target_z": -0.40820310412755634, "ce": 6.173524379730225, "genuineness": 4.595211505889893, "identity": 0.6852321624755859, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0d1b1573d32b8fce463207bb0d98802a0b7239deb33721fe8942d7766943e1e6.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": "0d848fdace054b887603c2a6578ed1865b0eeb361e3fe623119e1b81d66adb64", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "99b66a1eb0470735e55153e0552e80be8ca628b8873cacd728692b4566aaadc5", "generation_seconds_batch": 28.206361901015043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1752431392669678, "target_z": 1.164062551265651, "ce": 5.414999485015869, "genuineness": 4.557555198669434, "identity": 0.5776937007904053, "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_Longing/0d848fdace054b887603c2a6578ed1865b0eeb361e3fe623119e1b81d66adb64.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "0e1ffedc5c00ea45de5301b83f264fe1d039db0ccee3fc15e10a8b7325a0f2af", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f1ef014d0ebd9ebd825db585e0a7ff38a125df0575c42bd6e8ce8ba9a9034f79", "generation_seconds_batch": 18.026870685978793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0436062812805176, "target_z": 0.9570313459400042, "ce": 6.109982967376709, "genuineness": 4.482243061065674, "identity": 0.629245400428772, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0e1ffedc5c00ea45de5301b83f264fe1d039db0ccee3fc15e10a8b7325a0f2af.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": "0f03c062bf54f3c8c7361fe2bf0233cc078a92deb074a9dbb4af97bff09d6506", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96f0f45680a64df721d2d4c9160ba7cd2c6994f1388b020f466bbdcbf2c5d9f0", "generation_seconds_batch": 24.923399116960354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.35903799533844, "target_z": 1.453124985352671, "ce": 5.871703147888184, "genuineness": 4.595211505889893, "identity": 0.5433492660522461, "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_Longing/0f03c062bf54f3c8c7361fe2bf0233cc078a92deb074a9dbb4af97bff09d6506.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "0f0d1c66c0c50f3c5e08951a08bf54d7fbf47668713749519c4832d647bc00f6", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6be76c41f3ae9895c14e7fcf46ec213ec031e9ed2aad76be3f678cf9ed46c444", "generation_seconds_batch": 27.964692324982025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1504058837890625, "target_z": 1.124999882821369, "ce": 5.871703147888184, "genuineness": 4.645420074462891, "identity": 0.6382108926773071, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0f0d1c66c0c50f3c5e08951a08bf54d7fbf47668713749519c4832d647bc00f6.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "0fdd2e088641d8a43b955439b4e7a8414d47a5df6ee20d4f965d581ed1fd1d12", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d5b96835283e98d34b7061326c3ff155f44faac3c475d408ff9c6623f0d55674", "generation_seconds_batch": 21.931750096031465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4732887744903564, "target_z": 1.6328123227673206, "ce": 6.292664527893066, "genuineness": 4.030367851257324, "identity": 0.493561327457428, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/0fdd2e088641d8a43b955439b4e7a8414d47a5df6ee20d4f965d581ed1fd1d12.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "104bb3a396d4c7e7e0690ed5e1fb1d2170dbfadc75eac1a1a84abfa10b167609", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1f7b51f7eaacc488735209a200387a76288b7e81f4cd0b0df6c6a437cb967087", "generation_seconds_batch": 21.54892024595756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30780571699142456, "target_z": -0.20019528521934996, "ce": 6.332377910614014, "genuineness": 4.168440818786621, "identity": 0.6484222412109375, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/104bb3a396d4c7e7e0690ed5e1fb1d2170dbfadc75eac1a1a84abfa10b167609.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "10987a1518eaf87fa89e3eb6c4bc2fe47c771396fee34aebe72eb9ba831b547e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bf6d360066fd0f630f5ee761e6f25d695efb156b676808d91d0ff5f5a6abf70e", "generation_seconds_batch": 21.88683728396427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1156339645385742, "target_z": 1.0703125219709932, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.588828980922699, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/10987a1518eaf87fa89e3eb6c4bc2fe47c771396fee34aebe72eb9ba831b547e.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "10b038523a1211f0bf0dc2c3119d8bd3fdcd6b377bef3766c6cba283bc140be4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "12e6dae4a2f1013ae4e5c38f114bc76338babf47d9aa23e51eab21463da39e4f", "generation_seconds_batch": 24.385836925008334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.210015058517456, "target_z": 1.2187499121160268, "ce": 6.213237762451172, "genuineness": 4.65797233581543, "identity": 0.7074509263038635, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/10b038523a1211f0bf0dc2c3119d8bd3fdcd6b377bef3766c6cba283bc140be4.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "11b8064b0b44e5809cc54875c8293a532f8eb0947c5f9831bbd5983ef499fea0", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2cb39ee8338b5e4699e0d1c08afbe66d664a1107d03e64d7a2f129d96c888c5d", "generation_seconds_batch": 25.037237051990815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6570837497711182, "target_z": 1.9218749443401502, "ce": 5.967014789581299, "genuineness": 4.507347106933594, "identity": 0.7506199479103088, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/11b8064b0b44e5809cc54875c8293a532f8eb0947c5f9831bbd5983ef499fea0.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "123babecbf3e73b4857af46bd12844fdfbbefdcbfffae1d42b59e84139c474e9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "be342afc08f5bbf8743debca2a5e38231ead2f61d3eee0d7be06788b4c3b1372", "generation_seconds_batch": 16.346255988930352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5478003025054932, "target_z": 1.7499999531285475, "ce": 5.498397350311279, "genuineness": 4.7332844734191895, "identity": 0.6459528207778931, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/123babecbf3e73b4857af46bd12844fdfbbefdcbfffae1d42b59e84139c474e9.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "123bd493e6e8b79d0bcc6518132a275d568138dd075937cc9a7d5e7627b18b91", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb15fbae26b6996e978f7c91f0b36e164fca710fbb169319a0441a6ba3ae04e6", "generation_seconds_batch": 19.458215913036838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3407149314880371, "target_z": -0.14843748388793823, "ce": 6.109982967376709, "genuineness": 4.2249250411987305, "identity": 0.4818437993526459, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/123bd493e6e8b79d0bcc6518132a275d568138dd075937cc9a7d5e7627b18b91.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "124cd017406cfdcef5748680f0d6e43ff11c1614d8e5c72a16b9b2903918f5b8", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1ab6e97265043866f55d719f18ba9213a8a358f77de53631b3876df6ff7a3378", "generation_seconds_batch": 24.503497874946333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2696242332458496, "target_z": 1.3124999414106844, "ce": 5.550024509429932, "genuineness": 4.093128204345703, "identity": 0.40185943245887756, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/124cd017406cfdcef5748680f0d6e43ff11c1614d8e5c72a16b9b2903918f5b8.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "00d7bd3169b2b7d1a4562a3bf654ceca42b787edc90f7922430305b49914dbce", "generation_seconds_batch": 19.844086594996043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.746497631072998, "target_z": 2.0625001757679464, "ce": 6.260893821716309, "genuineness": 4.250029563903809, "identity": 0.7251652479171753, "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_Longing/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "12b8d2670a02cfd4282d35916611b59a2e78c4912d6fc6f04a176c09c9adc1bc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "007eba5168815e196c88f0048e3cc525312c6f9a67b847e78dfa3c675b645ed9", "generation_seconds_batch": 22.877032682998106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2696242332458496, "target_z": 1.3124999414106844, "ce": 5.685050010681152, "genuineness": 4.457139015197754, "identity": 0.77638840675354, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/12b8d2670a02cfd4282d35916611b59a2e78c4912d6fc6f04a176c09c9adc1bc.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": "12ddf4b8026ceee909528c0f81bffb01cffda4a80dd1ee352f4b80cc56c9bb72", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c5b3a974bd8c7a8601db588c5048bc20b6b262f6f9f48d0e88a4ab05affcf184", "generation_seconds_batch": 19.942509043961763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.610830307006836, "target_z": 3.421875038083055, "ce": 5.2343034744262695, "genuineness": 4.319066047668457, "identity": 0.45858490467071533, "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_Longing/12ddf4b8026ceee909528c0f81bffb01cffda4a80dd1ee352f4b80cc56c9bb72.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": "12f7339a218f8a4bea71d506dba99bd33b873058334a8e61d7b1370f040620d1", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b69016c7f059f7c0201510e68d95298fb23d024e2107139165461a25211e8f02", "generation_seconds_batch": 21.128862797049806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2944614887237549, "target_z": 1.3515626098549667, "ce": 5.34748649597168, "genuineness": 4.469690799713135, "identity": 0.5854922533035278, "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_Longing/12f7339a218f8a4bea71d506dba99bd33b873058334a8e61d7b1370f040620d1.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "134e268090db790a9e2542644da64ed5bef40c75741ef94cfe3f9bb68cefb8ec", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8b30a73aa5e403880e406272d5955b466a6bd7d6f6f9255d757a3202d2c7183c", "generation_seconds_batch": 16.627210465958342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7654301524162292, "target_z": 0.5195312404792363, "ce": 6.125868320465088, "genuineness": 4.595211505889893, "identity": 0.5598819851875305, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/134e268090db790a9e2542644da64ed5bef40c75741ef94cfe3f9bb68cefb8ec.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "139ffd6b875003850bf71d11279355d0427acc299482cca1ce4afe2fc28cd4cc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f03ff83d63f9cc0d01cbf1bffed6bde5336bd27653bd8f14da7a95d048ed35b0", "generation_seconds_batch": 25.328850010060705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9442576169967651, "target_z": 0.8007812346203047, "ce": 6.038498878479004, "genuineness": 4.582659721374512, "identity": 0.44888216257095337, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/139ffd6b875003850bf71d11279355d0427acc299482cca1ce4afe2fc28cd4cc.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": "13a69251c6d1a9f96127ed67e15519ad4b4f290df76e4ba5700cf0c375c7335f", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cac1ffba251713d91f4ae0809b6ddf3d23179d6cf78e3a75769fe49b7e5770c7", "generation_seconds_batch": 17.485605148016475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3938100337982178, "target_z": 1.5078125336888564, "ce": 5.9431867599487305, "genuineness": 4.770940780639648, "identity": 0.5217682123184204, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería. La colocaremos después de comer.", "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_Longing/13a69251c6d1a9f96127ed67e15519ad4b4f290df76e4ba5700cf0c375c7335f.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": "13ff0bb6a20e8e10f081959b5501ef39afa3b38dd8ebc51a788c330929618e63", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3811b94363b37396ea5d1243aca71becbca84dccd51fe3c0a88e5791f9be4d08", "generation_seconds_batch": 15.329897007904947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.979029655456543, "target_z": 0.85546878295649, "ce": 6.173524379730225, "genuineness": 4.595211505889893, "identity": 0.5481066107749939, "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_Longing/13ff0bb6a20e8e10f081959b5501ef39afa3b38dd8ebc51a788c330929618e63.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "140ccabeef2e8d1f9e9a0640ef37f4bf27be6da116f43d75194d2d0d62245a8c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "31379f79e9baa864c321ab1e7250cce1dda609d33b9e8f1649d789c92b3edff6", "generation_seconds_batch": 24.385836925008334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4832236766815186, "target_z": 1.6484373901450333, "ce": 6.086154937744141, "genuineness": 4.6203155517578125, "identity": 0.7530820369720459, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/140ccabeef2e8d1f9e9a0640ef37f4bf27be6da116f43d75194d2d0d62245a8c.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "14200e675a6e0096906de669afe14aa9366a190cc153f170048f4ae36eab4085", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "cbb0119bfa8abe1d26f0fbd507fa41bce56c769bce123e19805922012f5cf4b5", "generation_seconds_batch": 23.785134401987307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.084282636642456, "target_z": 2.5937498418088483, "ce": 5.585766792297363, "genuineness": 4.519899368286133, "identity": 0.6459386348724365, "hypothesis": "La porte 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_Longing/14200e675a6e0096906de669afe14aa9366a190cc153f170048f4ae36eab4085.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": "14b288a6e680258cefd0548b61a11fda151fe6b8e33464de027bc6432886940a", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "707a6abe8170260594646d32ccd355301ec49d0bda51dedd73437a7360c9daa8", "generation_seconds_batch": 15.329897007904947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7318999767303467, "target_z": 0.46679682556526503, "ce": 6.0305562019348145, "genuineness": 4.331617832183838, "identity": 0.5162436962127686, "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_Longing/14b288a6e680258cefd0548b61a11fda151fe6b8e33464de027bc6432886940a.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "bf275f190bb8c280f5868999531385468cd9a96b90e132219059f658a847cf74", "generation_seconds_batch": 16.57668074395042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17803159356117249, "target_z": -0.40429688415458054, "ce": 6.2767791748046875, "genuineness": 4.306513786315918, "identity": 0.4765109419822693, "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_Longing/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "15d3151c2131d7e83c3fa29b6c87147ed1bd73db753b6c5f7d5b12b580254a4e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b624d92c5cbb4706aa66677dc7cf17eaf4fa8d011324a9990d153ba574823133", "generation_seconds_batch": 24.86432381195482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0758945941925049, "target_z": 1.0078126274317614, "ce": 6.125868320465088, "genuineness": 4.3881025314331055, "identity": 0.7121192216873169, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/15d3151c2131d7e83c3fa29b6c87147ed1bd73db753b6c5f7d5b12b580254a4e.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "16ce6f85a92f71abc8d879917912cc5b328c0a4cd1796da277edfac48697e0b2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "635da300b9fe47c581657fe39d87fa492ff69abb63128d1ab82f5a6a9031ec33", "generation_seconds_batch": 23.708867541048676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3295381963253021, "target_z": -0.16601563781641276, "ce": 6.022613525390625, "genuineness": 4.432034492492676, "identity": 0.511215090751648, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/16ce6f85a92f71abc8d879917912cc5b328c0a4cd1796da277edfac48697e0b2.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "1791315a04b33bbe4c86641f08e3509c21e879db23771aed4111fe3d8d7b68d2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b8d7339f9a0bb6476530389425a514af2f6221db5c85b0eb2db9176a4ffda020", "generation_seconds_batch": 22.49442011292558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05012029409408569, "target_z": -0.6054687360850376, "ce": 6.125868320465088, "genuineness": 4.482243061065674, "identity": 0.6580553650856018, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1791315a04b33bbe4c86641f08e3509c21e879db23771aed4111fe3d8d7b68d2.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": "17a57b460b735aef56c23c4a82183e003ab2e052fefb54ce64e29b399c401da3", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b332bfeee191279346e4349fa022e20377cfac0cf31aeab824c301a39e83589a", "generation_seconds_batch": 16.560789759038016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5468632578849792, "target_z": 0.1757812580560309, "ce": 5.927301406860352, "genuineness": 4.049196243286133, "identity": 0.5103452801704407, "hypothesis": "I wrote the number on the envelope, read it carefully, and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/17a57b460b735aef56c23c4a82183e003ab2e052fefb54ce64e29b399c401da3.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "17b913e8ebe5ceb6ea70eab0bd2d0a3286d8c65bae9ad9ece10a1105fdad719d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6af1ba4e587e6feefa2d9dba129f551691b72da28a16bd5d12f643eae15afd7e", "generation_seconds_batch": 24.965252780006267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3084266185760498, "target_z": -0.19921876537969532, "ce": 6.205295085906982, "genuineness": 3.8420867919921875, "identity": 0.3207176923751831, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/17b913e8ebe5ceb6ea70eab0bd2d0a3286d8c65bae9ad9ece10a1105fdad719d.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "17cda55f84833ce40f04924a401825dbf9b185fa668b5cd28bef9ffda3947b9b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "392de68bc4246a6d07dffb7ada58426add747f22ba2e8eb9c10bd94d02d389aa", "generation_seconds_batch": 23.597163800965063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8076533079147339, "target_z": 0.5859374956058013, "ce": 6.181467056274414, "genuineness": 4.7834930419921875, "identity": 0.7985327243804932, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/17cda55f84833ce40f04924a401825dbf9b185fa668b5cd28bef9ffda3947b9b.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "17edc5d68e830094e09f8d32d9c6c87be2b70fac897f2b1066334774449b52ee", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97817bbf7733ea2b23184549b00dc694ff654f23ad08721d3b7308001c735842", "generation_seconds_batch": 17.781038894085214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0038667917251587, "target_z": 0.8945312639149624, "ce": 5.990842819213867, "genuineness": 4.532451152801514, "identity": 0.6026544570922852, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/17edc5d68e830094e09f8d32d9c6c87be2b70fac897f2b1066334774449b52ee.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": "1844ca5808f5688659d97c838d9ffe5031527781f799322b215f6d4f4c7b50e0", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b92e276d61ff3f790fa4a7dee19cc2a24c1c6eb35fa03ae0c9fddeace980d63e", "generation_seconds_batch": 19.54810117604211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.436337947845459, "target_z": 0.0019531334222141063, "ce": 5.6334228515625, "genuineness": 4.545003414154053, "identity": 0.11275190114974976, "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_Longing/1844ca5808f5688659d97c838d9ffe5031527781f799322b215f6d4f4c7b50e0.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "19679c7e1810d7ed48e98c4554dbaec169218285654418fb068164440bcaaca4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "af723e6c4c7383d57c9c708e37461fb6f1cc2be057fded913fb13bbda0561825", "generation_seconds_batch": 24.317044410970993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.319298505783081, "target_z": 1.3906249033276294, "ce": 6.046441555023193, "genuineness": 4.8588056564331055, "identity": 0.6283800601959229, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/19679c7e1810d7ed48e98c4554dbaec169218285654418fb068164440bcaaca4.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": "1a19e6049b5b68c5c45f11528addb4a987c4783d30600bbafea3d711a8af230d", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a2dca503b8672e69ac8742b70f06a9bd58d35ce419cfdaeaac876bacf1f6760", "generation_seconds_batch": 15.010896622086875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7927510142326355, "target_z": 0.5624999882821369, "ce": 5.486483573913574, "genuineness": 4.369274139404297, "identity": 0.5236359238624573, "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_Longing/1a19e6049b5b68c5c45f11528addb4a987c4783d30600bbafea3d711a8af230d.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "1a9cb5d9abd720cef1395c801b1ba5146452d85a16f64ff2ac02671d94767912", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ec434c1fa3b7039360e44fc45d471cf1f299080b15b7551b8d2ef7aea1b3fce7", "generation_seconds_batch": 18.073447249014862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5990212559700012, "target_z": 0.257812486817404, "ce": 6.24500846862793, "genuineness": 4.20609712600708, "identity": 0.3353092074394226, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1a9cb5d9abd720cef1395c801b1ba5146452d85a16f64ff2ac02671d94767912.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "1abcc438e4adcd390071434b2ecccdee8657dde71760e88a145f33956d5fc9ea", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a2c5d673a85c6551b0c14b5b4f6cbff496e36d448dcd100a9572f18fcc84eef6", "generation_seconds_batch": 23.597163800965063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7629464864730835, "target_z": 0.5156250673777129, "ce": 6.173524379730225, "genuineness": 4.720732688903809, "identity": 0.7741826772689819, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1abcc438e4adcd390071434b2ecccdee8657dde71760e88a145f33956d5fc9ea.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": "1ac8cd6ca1afd74c6cb1d49aff8e9a2f3b73a22728c97dd45c1166d887c51a42", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9cb4f3dab61062b7e40db53b69b45cf5e9f1c93a4c0b36be922e7cbde5ced1a3", "generation_seconds_batch": 19.03680490399711, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9467413425445557, "target_z": 0.8046875014647329, "ce": 5.418970584869385, "genuineness": 4.507347106933594, "identity": 0.8001587986946106, "hypothesis": "Quelqu'un a déplacé la petite chasse bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1ac8cd6ca1afd74c6cb1d49aff8e9a2f3b73a22728c97dd45c1166d887c51a42.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "1b04bfd0a5566a3b05df003fbb6463f997854ea0b9a7c24725d4cfd6a1fac13c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c0c11d42d319c3c725c498545dd4c153bd009eb489171265095413e44554432f", "generation_seconds_batch": 23.766848879982717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6074094772338867, "target_z": 1.8437499824232053, "ce": 5.895530700683594, "genuineness": 4.720732688903809, "identity": 0.47227075695991516, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1b04bfd0a5566a3b05df003fbb6463f997854ea0b9a7c24725d4cfd6a1fac13c.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": "1bc1066ccb870f6f89e05ef357038c8aa606165bf6d7b449864bf8464949929b", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "edab6ec6e860bb785aa6b344e0bdd140516bf49caee15062e3dc508ecc4b448f", "generation_seconds_batch": 23.880480770021677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8250393271446228, "target_z": 0.613281269773894, "ce": 6.09409761428833, "genuineness": 4.457139015197754, "identity": 0.7171902656555176, "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_Longing/1bc1066ccb870f6f89e05ef357038c8aa606165bf6d7b449864bf8464949929b.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "1bd4c13e4e22badc8fc468cfd2461e4bdd6e14ecde5d617e791d4d8e5a847645", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c781c97588952b60efbda86575a7a6898ca4597ce9153371d4eb82c71d432629", "generation_seconds_batch": 25.22005522705149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9054553508758545, "target_z": 2.3125001288964944, "ce": 6.356205940246582, "genuineness": 4.7332844734191895, "identity": 0.46337366104125977, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1bd4c13e4e22badc8fc468cfd2461e4bdd6e14ecde5d617e791d4d8e5a847645.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "1bf5e4f52deef0812f1376aa7900f24e1cc9951b4c52ea4239071b90cdb8f6fa", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0cb691dceae21ed7e6bab35422e9b031a679f9eeff4c09041817b86ea739c614", "generation_seconds_batch": 24.838693060097285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17927345633506775, "target_z": -0.40234375073236645, "ce": 6.205295085906982, "genuineness": 4.457139015197754, "identity": 0.5822640061378479, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1bf5e4f52deef0812f1376aa7900f24e1cc9951b4c52ea4239071b90cdb8f6fa.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": "1c25daa8785b68dd8b616a7d84c0592f2db962e016c7bb86925004870d786ffe", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6bc1ddace33d7e8de83ce2c5db04ae10d995f2a89ff01f9d12291115ceb61c84", "generation_seconds_batch": 16.778781992034055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1702756881713867, "target_z": 1.1562500175767947, "ce": 5.629451274871826, "genuineness": 4.419482707977295, "identity": 0.42401444911956787, "hypothesis": "The keys are on the kitchen table, like check the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1c25daa8785b68dd8b616a7d84c0592f2db962e016c7bb86925004870d786ffe.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "58f1df921d26cd8b095df1e9d2e3dcccf5f6c694e090667b136db5c6c32f2eab", "generation_seconds_batch": 17.472337134066038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06999000906944275, "target_z": -0.5742187419439692, "ce": 6.205295085906982, "genuineness": 4.532451152801514, "identity": 0.7048578262329102, "hypothesis": "Escribí el número en el sobre. Léela 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_Longing/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579", "bucket": "emo_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "80134dea6b13d006eed5b964a900d36330d18e81dc099e4cb454da7be316259b", "generation_seconds_batch": 19.883663478074595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10227829217910767, "target_z": -0.5234375073236645, "ce": 6.284721851348877, "genuineness": 4.457139015197754, "identity": 0.6333980560302734, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suche in der Schublade. Dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "1dcf2eceb622aca5f8f34770fe0b9bf598dee2a941b44f725839ebf2752ba4b5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c13278e480dc14bcb6252c5bdec22b37571111a996b4b2b7f62524c6436c3d3d", "generation_seconds_batch": 23.76023220794741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3798334300518036, "target_z": -0.08691406231690839, "ce": 6.0305562019348145, "genuineness": 3.8546390533447266, "identity": 0.5555807948112488, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1dcf2eceb622aca5f8f34770fe0b9bf598dee2a941b44f725839ebf2752ba4b5.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": "1e2170fe6cfa122ff73f4a03a1ff91e38eacc709953ed43815c4caa2365a615a", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "60751a54c3dbce45c256d7f171ff9525a20ab07411aecabed514a7f2f6042593", "generation_seconds_batch": 17.485605148016475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3540706634521484, "target_z": 1.4453126391496243, "ce": 5.387199878692627, "genuineness": 4.168440818786621, "identity": 0.42767220735549927, "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_Longing/1e2170fe6cfa122ff73f4a03a1ff91e38eacc709953ed43815c4caa2365a615a.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "1eaaffef6a8bba40a88c27cbc31e743512552c3d269ed5fe70c4000020cbee2a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b47a96f3cee89a3578033f2e0f5ee430307755e0e36aea972d657319f7625501", "generation_seconds_batch": 24.319857925060205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.597779393196106, "target_z": 0.2558593533951899, "ce": 6.340320587158203, "genuineness": 4.369274139404297, "identity": 0.49592435359954834, "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_Longing/1eaaffef6a8bba40a88c27cbc31e743512552c3d269ed5fe70c4000020cbee2a.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d712cfa0bb4b43b658c665e480de97ab551a22203667f43830ea0daf823d0f2d", "generation_seconds_batch": 17.472337134066038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04515284299850464, "target_z": -0.613281269773894, "ce": 6.205295085906982, "genuineness": 4.419482707977295, "identity": 0.6003665328025818, "hypothesis": "Escribí el número en el en el sobre. Léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "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_Longing/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "1ed95100d4c8300723e97f450e5eefcd2d228fd5d0dac7bb6ef90b566c33e045", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb49b9aaa36dd8684bd09fbb2bec4319e7fb63aec573542f3b9af8bbf39c0559", "generation_seconds_batch": 26.526121389004402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.428581953048706, "target_z": 1.562499894539232, "ce": 5.935244083404541, "genuineness": 4.457139015197754, "identity": 0.23590970039367676, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het Auge 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_Longing/1ed95100d4c8300723e97f450e5eefcd2d228fd5d0dac7bb6ef90b566c33e045.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "1f501ada86532bb6763ce335281fe3097ff366db4be7c819af7745ce66f51e7d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4f145357b9a159848bca1b299d156fa0e80ab02ff23b883bccc02649a66baae5", "generation_seconds_batch": 20.41669654904399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8970670700073242, "target_z": 0.7265625395477879, "ce": 5.959072113037109, "genuineness": 4.325342178344727, "identity": 0.5139052867889404, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1f501ada86532bb6763ce335281fe3097ff366db4be7c819af7745ce66f51e7d.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "1f83a7e08c135b8f1a51a5b266a730a19cdd4934cf1fa135881bebfcd3a685e5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e6a90028d1d2cc24c0fb7142443e4bff7afcfc5c28e907431db9ee8b06880e42", "generation_seconds_batch": 24.80073210899718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.974999189376831, "target_z": 2.4218748505972454, "ce": 5.871703147888184, "genuineness": 4.7332844734191895, "identity": 0.6583932638168335, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1f83a7e08c135b8f1a51a5b266a730a19cdd4934cf1fa135881bebfcd3a685e5.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "1fe587e356305b824984424390b0dadfc7aceeadad2b8803da4002c8f31d5987", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a2fd934f39f2595331ddb397ba261baa66e99013feea4a27bfe9606dbbccce72", "generation_seconds_batch": 22.84741855307948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03770172595977783, "target_z": -0.6249999765642738, "ce": 6.133810997009277, "genuineness": 4.319066047668457, "identity": 0.80863356590271, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/1fe587e356305b824984424390b0dadfc7aceeadad2b8803da4002c8f31d5987.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "204b0f7e19424b979bdb4310436a6c6b86dc3e7e48bbd40c96c929d72da880ae", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "feab61ee340aaec26e500977b814606945c9644733518459992a1de375a0b2be", "generation_seconds_batch": 24.69651811895892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7763020992279053, "target_z": 2.1093750029294656, "ce": 6.268836498260498, "genuineness": 4.494794845581055, "identity": 0.35226595401763916, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/204b0f7e19424b979bdb4310436a6c6b86dc3e7e48bbd40c96c929d72da880ae.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "206e7ac367a391dcafb15b246c54993621628ddf9ab2a30212f7be137e3133b7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e76132f2c5bdcae69ce97b6e28098ebc20e3c9685dbbdb99318e640d3a6a4479", "generation_seconds_batch": 24.72040598199237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.627279281616211, "target_z": 1.875000117178631, "ce": 5.8875885009765625, "genuineness": 4.6956281661987305, "identity": 0.766670823097229, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/206e7ac367a391dcafb15b246c54993621628ddf9ab2a30212f7be137e3133b7.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": "2085504163f5eed8951e38a1e72216d9903d9bc2108603b1ad70df5ef90df546", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca21b46ea1760a26fa0ba7a1b77d2d3086a1ceed00b89e49e36374ea95b2fcca", "generation_seconds_batch": 24.23090143292211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.955129623413086, "target_z": 2.390625090813439, "ce": 5.458683967590332, "genuineness": 4.457139015197754, "identity": 0.5440901517868042, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich lass sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2085504163f5eed8951e38a1e72216d9903d9bc2108603b1ad70df5ef90df546.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "2099e4706bbd130e20a44452acfb125a87de75f30da6be3db8b014d7595d2147", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f1a811201a2df177ace371eee0f6d8a89191544b0be266a6bcf8eb8374d91c5", "generation_seconds_batch": 24.96476655092556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5332028269767761, "target_z": 0.15429688415458054, "ce": 5.530168056488037, "genuineness": 4.532451152801514, "identity": 0.665570855140686, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2099e4706bbd130e20a44452acfb125a87de75f30da6be3db8b014d7595d2147.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "20d15a2abd11802bd1049bb2d8d2c896f7aac5a557d5b57b8fe8766fd42c4bf6", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "52f55dfd405f8af7dfde59fee0b893fbce7e80daeb07bdafbcf98ef6112974cb", "generation_seconds_batch": 23.1860169460997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2745916843414307, "target_z": 1.320312475099541, "ce": 5.289902210235596, "genuineness": 4.482243061065674, "identity": 0.4762718677520752, "hypothesis": "He encontrado la cajita, estaba junto a la ventana, vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/20d15a2abd11802bd1049bb2d8d2c896f7aac5a557d5b57b8fe8766fd42c4bf6.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "2145f070c10e61ccbadac2798f97f2398e2496a22df39e53cdd7ca87db5d4610", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2f3ef03e99ea39d4f8ca1317d05584ced9e10c18408da920e0d17e5314ae2b91", "generation_seconds_batch": 21.708119458984584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8896158933639526, "target_z": 0.7148437390145034, "ce": 5.839932441711426, "genuineness": 4.7834930419921875, "identity": 0.6236062049865723, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2145f070c10e61ccbadac2798f97f2398e2496a22df39e53cdd7ca87db5d4610.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "219eaa840554744b62b0c34f0329c112185b7696db4db800b02684f9ae9df46a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f9e05b00681e0641871f632ba26154fd908d73962d32afd3407872bc8b91fd5f", "generation_seconds_batch": 25.07383648492396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5478003025054932, "target_z": 1.7499999531285475, "ce": 6.125868320465088, "genuineness": 4.507347106933594, "identity": 0.7320132255554199, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/219eaa840554744b62b0c34f0329c112185b7696db4db800b02684f9ae9df46a.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "220802bb08ac744979477da935ebe32cefe0b5bd73fa98bf32a8863c1d7e10bc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9fa173770ff544989e67b8e8e3152372340c0fc93c57f877a4ec36c1c21e37a9", "generation_seconds_batch": 25.3383045559749, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1802105903625488, "target_z": 1.1718750849545074, "ce": 5.824047088623047, "genuineness": 4.482243061065674, "identity": 0.49461430311203003, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/220802bb08ac744979477da935ebe32cefe0b5bd73fa98bf32a8863c1d7e10bc.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "225f37809f4669855e26784be1ca1cb9ce43c6b671d5122931543519de67c7bb", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ddbb54185f1a0da818a2059d141cded898d144d5181570769cd46cacf7a6faf0", "generation_seconds_batch": 23.11361532798037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.852360188961029, "target_z": 0.6562500175767947, "ce": 5.649308204650879, "genuineness": 4.494794845581055, "identity": 0.5864682197570801, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/225f37809f4669855e26784be1ca1cb9ce43c6b671d5122931543519de67c7bb.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "227e5786c759afc01cacc3cb905a7598fb38b0f7a2a5ebb426f03d659cd8a374", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "97775f814c40e9c4c19c2bbc795fd980fd93e5a67e3b7f4b8f08bdf0687b9bf7", "generation_seconds_batch": 18.46386583405547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7219651341438293, "target_z": 0.451171851930457, "ce": 5.744620323181152, "genuineness": 4.400654315948486, "identity": 0.49885293841362, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/227e5786c759afc01cacc3cb905a7598fb38b0f7a2a5ebb426f03d659cd8a374.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "22fa34f4a6ba73a191f95e473a006c3539228a385ec6028c981d10c1bcb3bf05", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0d40376a2b6fee5f6e68ac6be29a46d18a71850042db470d4a1811a1e05ce0cc", "generation_seconds_batch": 24.64933230704628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0907968282699585, "target_z": 1.031250041012521, "ce": 5.982900142669678, "genuineness": 4.65797233581543, "identity": 0.7634810209274292, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/22fa34f4a6ba73a191f95e473a006c3539228a385ec6028c981d10c1bcb3bf05.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "2300e464bd6d2f72da187b43ff7a239e33b3ab8513fbcb9f2ce2a3b0e8249778", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ce65d98c4747f83669e2783155ee2c2a03f90ca5aef0e60985938b99e9d54083", "generation_seconds_batch": 22.40926380001474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41491588950157166, "target_z": -0.03173830093234818, "ce": 6.260893821716309, "genuineness": 4.582659721374512, "identity": 0.5445072650909424, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2300e464bd6d2f72da187b43ff7a239e33b3ab8513fbcb9f2ce2a3b0e8249778.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "234d9bd9ab4d72a7f643b71ca31a817f2696c526311c981032eafe83d842a937", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "86a599e409e7421fafd653cc8713ec0d5984189e38a04e6df412f96807bbe077", "generation_seconds_batch": 26.27866603806615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.602746844291687, "target_z": 0.2636718870840463, "ce": 6.41180419921875, "genuineness": 4.344170093536377, "identity": 0.5124648809432983, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/234d9bd9ab4d72a7f643b71ca31a817f2696c526311c981032eafe83d842a937.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": "23e8489ab30bfe2fafe92db18ba8d0f79d6a7545c27f891b82862801edc5818f", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4dc7d0c5b10e80c41e06d6b5dee23740557cafac8753b1d818a2fa2a46a476f2", "generation_seconds_batch": 24.119873189018108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08737599849700928, "target_z": -0.5468750146473289, "ce": 5.982900142669678, "genuineness": 4.344170093536377, "identity": 0.23280389606952667, "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_Longing/23e8489ab30bfe2fafe92db18ba8d0f79d6a7545c27f891b82862801edc5818f.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "25468d3a60b6096e0ea8f31cb1dc2dbc33dbf1dc0cc02d11c4ed3b335ec8a53e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "62f4cdea58c9c98622b5ee29bcc0808b934b1c808e614d3c93d566abe1878aa2", "generation_seconds_batch": 24.515410411986522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4782562255859375, "target_z": 1.640624856456177, "ce": 6.213237762451172, "genuineness": 4.469690799713135, "identity": 0.748062014579773, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/25468d3a60b6096e0ea8f31cb1dc2dbc33dbf1dc0cc02d11c4ed3b335ec8a53e.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "25c496cd43f7e5d5901788342f5e0ea177f99ce9b80efa2cd40dd14065366f1a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "269d62f766f351ed9c334dcb24d8d2e2ce513b12f492afcd8681c263afb546b7", "generation_seconds_batch": 24.537110147066414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6263421177864075, "target_z": 0.30078123462030465, "ce": 6.125868320465088, "genuineness": 4.595211505889893, "identity": 0.7455819845199585, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/25c496cd43f7e5d5901788342f5e0ea177f99ce9b80efa2cd40dd14065366f1a.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "25d7f67e5a0e82ef728d0a7909342a5938e337a4c090904d82d5544245c73f7a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "edd6aabad62bec09ac76226c37efab18d1a84d382699007225d7c9912e9158ad", "generation_seconds_batch": 24.56808274006471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21901290118694305, "target_z": -0.3398437390145033, "ce": 5.998785495758057, "genuineness": 4.3504462242126465, "identity": 0.5369666814804077, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/25d7f67e5a0e82ef728d0a7909342a5938e337a4c090904d82d5544245c73f7a.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "25dbd44a02cde0f4f29aba6e6d63d07e68a3e51f8c54a7c15c85f0f3cfd1dbba", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "edcfeceda8b928ca3f13af63e279310dc11a032476da2e815750309343bc6fa6", "generation_seconds_batch": 17.955596353043802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3596532344818115, "target_z": -0.11865236324925657, "ce": 6.149696350097656, "genuineness": 4.582659721374512, "identity": 0.7073241472244263, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/25dbd44a02cde0f4f29aba6e6d63d07e68a3e51f8c54a7c15c85f0f3cfd1dbba.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "25e46f83f46a8b97918040d04a399c138482d9259293aba2d82063f7ecbc4c78", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4fe501f21ac853a2355a1cb4c46f7cf470dcbcdb3aad108e488329985236f96d", "generation_seconds_batch": 18.84497840795666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7862370014190674, "target_z": 2.1250000703071787, "ce": 5.593709468841553, "genuineness": 4.582659721374512, "identity": 0.7977769374847412, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/25e46f83f46a8b97918040d04a399c138482d9259293aba2d82063f7ecbc4c78.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "265d8377402db8745c6f7338ed0daf3aa67e2fc41ecb87b2e00a58cfef87d992", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "eb963923d242dc0b780fa5a1661cd4c34d1fa2ba7ff920c1da5d277bb6506ea7", "generation_seconds_batch": 18.183218426071107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2426081895828247, "target_z": -0.3027343680425188, "ce": 6.300607204437256, "genuineness": 4.607763767242432, "identity": 0.4690912365913391, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/265d8377402db8745c6f7338ed0daf3aa67e2fc41ecb87b2e00a58cfef87d992.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "26ca88b6c5b86f69d2164d6734940a41d575eeff94184ffe53b653d09dac403c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d2ba23c53a4b56fe30777186033064f84071f2782c56eb9fd946f82f1caa6cd", "generation_seconds_batch": 20.42335507401731, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7067580223083496, "target_z": 1.9999999062570952, "ce": 5.7128496170043945, "genuineness": 4.607763767242432, "identity": 0.8332700133323669, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/26ca88b6c5b86f69d2164d6734940a41d575eeff94184ffe53b653d09dac403c.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "f62684439f2de3e7e98a2dcbd6428d247087d5050eb53b2723ff62f719487b44", "generation_seconds_batch": 19.043600006960332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06253886222839355, "target_z": -0.5859374956058013, "ce": 6.38003396987915, "genuineness": 4.325342178344727, "identity": 0.24864894151687622, "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_Longing/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "27352e2643cb2d0083620831de38c85c459e11740dd85e1f8c64cfa737651481", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a4d47c6140df4bd88a2d82fc8d5f853312402d10001118138008414c186638ab", "generation_seconds_batch": 22.389436692930758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.35903799533844, "target_z": 1.453124985352671, "ce": 6.062326908111572, "genuineness": 4.394378662109375, "identity": 0.673915445804596, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/27352e2643cb2d0083620831de38c85c459e11740dd85e1f8c64cfa737651481.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "279ef5b8b103433f7be68f344efb62c0e3fc6c47fdc0c6c2c4f49ecbcc68d913", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "19e84c274b2225d311b29a3ace43a6845dd2b64ee61164ffb4a1542a9a4b7a28", "generation_seconds_batch": 22.877571549033746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3391683101654053, "target_z": 1.4218750380830552, "ce": 5.804190158843994, "genuineness": 4.494794845581055, "identity": 0.5538530349731445, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/279ef5b8b103433f7be68f344efb62c0e3fc6c47fdc0c6c2c4f49ecbcc68d913.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "27a04e8a8739feeb1132dad19f307d43211149a49cf3eb615633e870c656608a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5492b80685a3d9a7212332a2f8cd86582a0fb5babaadf7c3be2fa2d870dbfd71", "generation_seconds_batch": 24.14028445398435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.663597822189331, "target_z": 0.35937495605801334, "ce": 6.125868320465088, "genuineness": 4.356721878051758, "identity": 0.3663417100906372, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/27a04e8a8739feeb1132dad19f307d43211149a49cf3eb615633e870c656608a.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "281962138da1e73f7adb406c798a327660a10e4e988755cf20c72a3231271a79", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "333288c0343b2885ca5b54c2253772c8ab9680666400f25151574053da6aa7c4", "generation_seconds_batch": 24.24957196705509, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7166929244995117, "target_z": 2.015624973634808, "ce": 5.3792572021484375, "genuineness": 4.381826400756836, "identity": 0.5010435581207275, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/281962138da1e73f7adb406c798a327660a10e4e988755cf20c72a3231271a79.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "28f646476a674c57ac16f6a01788496645b5e52bad170f70bc5bbeb9a66e4e15", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a55f6cdbd8f0e5d135b33e4a10efced6dd7ae380cac6e5387479522d9377f48e", "generation_seconds_batch": 25.625678005977534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9417738914489746, "target_z": 0.7968749677758764, "ce": 6.109982967376709, "genuineness": 4.545003414154053, "identity": 0.49664604663848877, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/28f646476a674c57ac16f6a01788496645b5e52bad170f70bc5bbeb9a66e4e15.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "2901be4839be5d56320db5a0b7b55e4af2238fd68b2a4124960aea9a822e2e53", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d006d5dacdf142a0ca77260900a01eb8d19b7945a88abdb39978788c49c6cdf3", "generation_seconds_batch": 23.723022207035683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14325958490371704, "target_z": -0.45898438561931343, "ce": 6.229123115539551, "genuineness": 4.406930446624756, "identity": 0.7407441139221191, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2901be4839be5d56320db5a0b7b55e4af2238fd68b2a4124960aea9a822e2e53.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "29662f2d206459ada4331c3dbcdceee023023d2e5058f1b73b06f942225b88da", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "07d0c524a1f4ac0d3cab5856dde756c5ced136c3fb32a4f4b2e923828c0b057f", "generation_seconds_batch": 24.585544439032674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6074094772338867, "target_z": 1.8437499824232053, "ce": 6.372091293334961, "genuineness": 4.632867813110352, "identity": 0.4555445909500122, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/29662f2d206459ada4331c3dbcdceee023023d2e5058f1b73b06f942225b88da.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "296f40bbbef97786d6cfd64b46f2941e1add22ee158c7ca37f4d1b1a3b5377cb", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f19e3a709f56557bef1403cb4fbaad264b24fc775d8a1e5dd8e9718672a3cf85", "generation_seconds_batch": 21.961116733960807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0709271430969238, "target_z": 1.0000000937429048, "ce": 5.990842819213867, "genuineness": 4.293961524963379, "identity": 0.5682376623153687, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/296f40bbbef97786d6cfd64b46f2941e1add22ee158c7ca37f4d1b1a3b5377cb.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "298e6dd3ceedb4a5c5139013e3fdc00e929be8a156c520401df2d2e2ab1e1f7e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3e979a393a7068a41848a2e9d1bf9b175d6996c2d0c33f991bd4e16b0a679359", "generation_seconds_batch": 24.859617750975303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0063505172729492, "target_z": 0.8984375307593907, "ce": 5.855817794799805, "genuineness": 4.65797233581543, "identity": 0.6124650239944458, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/298e6dd3ceedb4a5c5139013e3fdc00e929be8a156c520401df2d2e2ab1e1f7e.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "29ddaa67c4c5213307f5c32ee7547a931cc145c5b5024c342b5326f08c4c7a01", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1910255846b8b3fb790cd09cdc7937fbc19d988a751b7e4793b13fe0070e6704", "generation_seconds_batch": 19.39797405397985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46241694688796997, "target_z": 0.04296874780290067, "ce": 6.221180438995361, "genuineness": 4.306513786315918, "identity": 0.17788612842559814, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/29ddaa67c4c5213307f5c32ee7547a931cc145c5b5024c342b5326f08c4c7a01.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "2a1f763eb15bced42c5725d6304c5dca2afab858224333f88f80dfd3bf55751e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "982ed134a7ad1d38192cb36e3ba6681de3a75b183de6b16e01531d74bdb7769f", "generation_seconds_batch": 29.05902374209836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1702756881713867, "target_z": 1.1562500175767947, "ce": 6.109982967376709, "genuineness": 4.557555198669434, "identity": 0.4657052755355835, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2a1f763eb15bced42c5725d6304c5dca2afab858224333f88f80dfd3bf55751e.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "2a2bf70c19fe50988f5cfd8f5e1298aecd3387efad8f343791966f7c21bca53d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "11cc28c888e0d1c45105fdb6d190e9b1756c4c961046508871abd728454353a5", "generation_seconds_batch": 21.708119458984584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3540706634521484, "target_z": 1.4453126391496243, "ce": 5.911416053771973, "genuineness": 4.68307638168335, "identity": 0.6675218343734741, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2a2bf70c19fe50988f5cfd8f5e1298aecd3387efad8f343791966f7c21bca53d.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "2a3b3f6c76c277f562aad7b6de779e6204c3338ebb2a7182756ec4c2cb36c505", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "293504ab4158fd7d00265352de9c858f914a4597b0f26909e1aa4128e03f0f96", "generation_seconds_batch": 24.696026649908163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.09576416015625, "target_z": 1.0390623872155675, "ce": 5.935244083404541, "genuineness": 4.093128204345703, "identity": 0.4476248323917389, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2a3b3f6c76c277f562aad7b6de779e6204c3338ebb2a7182756ec4c2cb36c505.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "2acf47de4f34ec70e91c37b623be03eefa409325063c263a249d33d54f9c1851", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a7f53a5c20eaf9926879094e0e45834c55ba71353cb6840a1cf613d0c0d47f62", "generation_seconds_batch": 21.951000688015483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3689727783203125, "target_z": 1.4687498652445743, "ce": 5.732706069946289, "genuineness": 4.13078498840332, "identity": 0.5592195987701416, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2acf47de4f34ec70e91c37b623be03eefa409325063c263a249d33d54f9c1851.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "2b9bbd22862d3c1d5bb02723726d8383e03a87a316d5de35891a26a01fd6a587", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d5ab36081bc9400bedf03b8b5467e08dfbb0ca7fe62b7841c54b6c5be33626f6", "generation_seconds_batch": 22.299476418062113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6586304306983948, "target_z": 0.3515625161120618, "ce": 5.967014789581299, "genuineness": 4.482243061065674, "identity": 0.6874989867210388, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2b9bbd22862d3c1d5bb02723726d8383e03a87a316d5de35891a26a01fd6a587.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "2bb1b6b344ccf228feeb8599d2a5337df61a31b957cb7444945f2cf0e4844192", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "593c5557dbf0d3e0fc62ac6808ee499d199e1d4f1a62d87145838badde57446d", "generation_seconds_batch": 22.546284900978208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.145438551902771, "target_z": 1.1171875366183222, "ce": 5.831989288330078, "genuineness": 4.570107460021973, "identity": 0.17982345819473267, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2bb1b6b344ccf228feeb8599d2a5337df61a31b957cb7444945f2cf0e4844192.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": "2bdfa6984755d2a52fb0bda2cfe528bd335bac893b6f1f833310f3d21d16f93e", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "70617c09d435271f59073e917e2543eadf6ec98245b4fce6095802b64f81ad37", "generation_seconds_batch": 19.022052870946936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.974999189376831, "target_z": 2.4218748505972454, "ce": 5.839932441711426, "genuineness": 4.482243061065674, "identity": 0.6328837871551514, "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_Longing/2bdfa6984755d2a52fb0bda2cfe528bd335bac893b6f1f833310f3d21d16f93e.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "2cc18a2953af8d86a38a67a704cc24f9ffc4216a76ced3822ff8158c0a3ecfb1", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57123b2995d7916168177f9a70896b82f757d1c096b463e88323b453bc913d3b", "generation_seconds_batch": 25.506421179976314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32270798087120056, "target_z": -0.17675782476713794, "ce": 6.038498878479004, "genuineness": 4.532451152801514, "identity": 0.707107663154602, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2cc18a2953af8d86a38a67a704cc24f9ffc4216a76ced3822ff8158c0a3ecfb1.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "2d654f15db074cef8499cbeb6e26a59fd5908878495ee28e4ea9fba9cf81be3e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f25a64ab42a852de69f13bae0c93f1f2841146f445284415fc71c030ed0caf2f", "generation_seconds_batch": 18.913494226057082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4909796714782715, "target_z": 0.08789062902801545, "ce": 5.871703147888184, "genuineness": 4.381826400756836, "identity": 0.5448406934738159, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2d654f15db074cef8499cbeb6e26a59fd5908878495ee28e4ea9fba9cf81be3e.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "2d793ffd5be895bdf125cc5354b143a5b7396cc1cc45b3fc83ab0092fc24259a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "068cb7dce45b2ef29916e9472d56b8f30083dcd9a18bdfef01c7d39958921f38", "generation_seconds_batch": 25.482424073969014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05260398983955383, "target_z": -0.6015625161120618, "ce": 5.982900142669678, "genuineness": 4.507347106933594, "identity": 0.5050568580627441, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2d793ffd5be895bdf125cc5354b143a5b7396cc1cc45b3fc83ab0092fc24259a.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "2d9c5381ff52677ff5f345a82bdf292fcaeba08a7f9dad326752bfd49c1e8b21", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "458e6ec9922fdd87d8237c8e039b3f3fc27ee7dde9057cfd31e2eb9c5dc21440", "generation_seconds_batch": 23.584301147959195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0560247898101807, "target_z": 0.9765624926763355, "ce": 5.95112943649292, "genuineness": 4.337893962860107, "identity": 0.807090163230896, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2d9c5381ff52677ff5f345a82bdf292fcaeba08a7f9dad326752bfd49c1e8b21.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "2e14e39cfcae231fc91e6632a6e47e55019ac9810b98b3d6633501d0222bde8f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "78bd889bb6d86c98ac107a56466753b528e0cae67086073bd6d76a52f4fd33c3", "generation_seconds_batch": 24.56808274006471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22894775867462158, "target_z": -0.3242187419439691, "ce": 6.141753673553467, "genuineness": 4.557555198669434, "identity": 0.7937092781066895, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2e14e39cfcae231fc91e6632a6e47e55019ac9810b98b3d6633501d0222bde8f.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "2e852a76fb8328a7cea0b5e07ed3ef7c43947d7fc91ff8ea9910a1da9ed21372", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fb70cc3e29876071632cf1225379f34446423044470a220b857292c035089bb7", "generation_seconds_batch": 17.13366259203758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49594709277153015, "target_z": 0.09570311584541945, "ce": 6.268836498260498, "genuineness": 4.557555198669434, "identity": 0.662787914276123, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/2e852a76fb8328a7cea0b5e07ed3ef7c43947d7fc91ff8ea9910a1da9ed21372.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": "2e8ac7c0b26e3d9f44eb45e4bb2386622b7e1c94dfc18f18a766a7bbdc576800", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bbe11919e0e9f7faeb8a4f85bc27455080ac55449aa17014b8058aa93213d98e", "generation_seconds_batch": 17.1694810759509, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1305363178253174, "target_z": 1.0937501230375626, "ce": 5.700935363769531, "genuineness": 4.545003414154053, "identity": 0.24006497859954834, "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_Longing/2e8ac7c0b26e3d9f44eb45e4bb2386622b7e1c94dfc18f18a766a7bbdc576800.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "301735aaa17ae5a9d7c01e2852bb3805bdf7d9a3782e9445a0fee2c4e35929de", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8cd216bd18375e89e145518c726c9239fe080e404892453b590a76240a51246f", "generation_seconds_batch": 23.785134401987307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4683215618133545, "target_z": 1.6250001640500835, "ce": 5.6413655281066895, "genuineness": 4.645420074462891, "identity": 0.6382865905761719, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/301735aaa17ae5a9d7c01e2852bb3805bdf7d9a3782e9445a0fee2c4e35929de.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "306932d1112cb78b52eb6af13cb78f7adb832899ef09577e3a83ca267163a9be", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cb14e684601dc7940c860d6d44c03579e2eefa03d24977b56f06e4992b482cc4", "generation_seconds_batch": 26.005900869960897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8359112739562988, "target_z": 2.2031250322241234, "ce": 6.324435234069824, "genuineness": 4.482243061065674, "identity": 0.22676680982112885, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/306932d1112cb78b52eb6af13cb78f7adb832899ef09577e3a83ca267163a9be.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "30bad108b5401af918b8e0979243bda0ea97d2b183ca9eca1985a44628435436", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9cfa9d2e4309ce35db0765b66a6ebaf50217630402f6c507aeec184c602210c4", "generation_seconds_batch": 25.328850010060705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7629464864730835, "target_z": 0.5156250673777129, "ce": 5.982900142669678, "genuineness": 4.758388519287109, "identity": 0.8018168210983276, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/30bad108b5401af918b8e0979243bda0ea97d2b183ca9eca1985a44628435436.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "32b110b4313fe610de9f246cc8638ddff98426b11f2c1dd9ae87a4324968af6a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c7b29593d3adb30e8d2a9b22b9156d7e9ad35b9659c690f45735ad8cd4b6e05c", "generation_seconds_batch": 17.792354698991403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2134358882904053, "target_z": 2.7968749677758766, "ce": 6.475345611572266, "genuineness": 4.7834930419921875, "identity": 0.3807436227798462, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/32b110b4313fe610de9f246cc8638ddff98426b11f2c1dd9ae87a4324968af6a.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "32c8f039ddbcb93e029ce8fc82e47a3cbab3ae16c9d5f2084ef028581a08fb33", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4e7a0071b7ee53afff2a5f227046920cba53dd8fc22336ca2ccb74b65cc8308f", "generation_seconds_batch": 28.541323916986585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9219042062759399, "target_z": 0.7656250205062605, "ce": 6.443574905395508, "genuineness": 4.557555198669434, "identity": 0.5772033929824829, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/32c8f039ddbcb93e029ce8fc82e47a3cbab3ae16c9d5f2084ef028581a08fb33.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "32d017d6c41d77684ccecb7a831a8a99fafa94d684cc0e90c094609a3346c6c6", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "849f100755fdf3ef44f896007cb9df0118d08db7bdb716180ab5abe4d0ee129c", "generation_seconds_batch": 25.083324313978665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7554953098297119, "target_z": 0.5039062668444282, "ce": 6.316492557525635, "genuineness": 4.262581825256348, "identity": 0.24617470800876617, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/32d017d6c41d77684ccecb7a831a8a99fafa94d684cc0e90c094609a3346c6c6.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "3364a45c49c44fb8348afad4ecaf30a8ee09ad15979276d3de73ddc1ff4a15d4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "11edcb3117501c0cdc707286eee9178101fb2ad27a56ee48c517c7fbff9183fa", "generation_seconds_batch": 24.689744382048957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9194204807281494, "target_z": 0.7617187536618322, "ce": 5.911416053771973, "genuineness": 4.281409740447998, "identity": 0.5194568634033203, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3364a45c49c44fb8348afad4ecaf30a8ee09ad15979276d3de73ddc1ff4a15d4.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "3365540fc6d6260a5a0297873e18c60c4b53ba93db414273ce168c97b38bf660", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4deef76717054bc0cb7aadffd21479c72b877e2a259ec057494acc12144e9f48", "generation_seconds_batch": 17.13366259203758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5779097080230713, "target_z": 0.22460940612557387, "ce": 6.1894097328186035, "genuineness": 4.65797233581543, "identity": 0.6837155818939209, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3365540fc6d6260a5a0297873e18c60c4b53ba93db414273ce168c97b38bf660.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "33b6ed5bd5bf39deee9d2fdcf6b01ab020beb9b05d575bb0b22576d803ce7396", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "eb7ea688838ac9471b1aeabd14ff7ff6c75f41bb3577facbb09cc9cec39aebda", "generation_seconds_batch": 25.29324460308999, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6934024095535278, "target_z": 0.40624997070534224, "ce": 6.268836498260498, "genuineness": 4.15588903427124, "identity": 0.3724437952041626, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/33b6ed5bd5bf39deee9d2fdcf6b01ab020beb9b05d575bb0b22576d803ce7396.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "c788993d8797f79d6c46140f3c3e1df30d7e64635d0b07d3df0d26eb9090d093", "generation_seconds_batch": 17.892103416961618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06750628352165222, "target_z": -0.5781250087883973, "ce": 6.173524379730225, "genuineness": 4.319066047668457, "identity": 0.5632312297821045, "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_Longing/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "345ccecfff9a21af103040ae2740ccefe96db6956fabbd7299fb50ac62f81336", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "50c982c0077712bb2418266d4805fa99907eb60cd53c89df997953de82ab5081", "generation_seconds_batch": 26.353880246984772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2537848949432373, "target_z": -0.2851562609854967, "ce": 6.332377910614014, "genuineness": 4.218649387359619, "identity": 0.3909482955932617, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/345ccecfff9a21af103040ae2740ccefe96db6956fabbd7299fb50ac62f81336.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "05b912305efac7808a427eaafe34224c80594461ca7a025dbfd299f1351ae4fb", "generation_seconds_batch": 18.693396004964598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7852998971939087, "target_z": 0.5507812814917571, "ce": 6.41180419921875, "genuineness": 4.2249250411987305, "identity": 0.2343357652425766, "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_Longing/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "heldout-es-1", "language": "es", "sentences": [ "Las llaves están en la mesa de la cocina.", "Miré en el cajón... y luego junto a la ventana.", "Llévatelas cuando te vayas." ], "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-1", "key": "348ff7708323a6caeb08848b1a502e9d13caaf817704b9b986b7d0cc82c492a6", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b9917bfa615e0e956d66dc5205d546818a15a9c7ad43b826d4812136d39b5bc0", "generation_seconds_batch": 17.3947963709943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7763020992279053, "target_z": 2.1093750029294656, "ce": 5.808161735534668, "genuineness": 4.419482707977295, "identity": 0.4596676826477051, "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_Longing/348ff7708323a6caeb08848b1a502e9d13caaf817704b9b986b7d0cc82c492a6.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "349235d48e88e8eacab5553edbaf5887beb0f27569d17cdb5939e42614cf98bb", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7e02382af97ba52b8f1ca2c1df8ef692a8834516807efe990ab6ecb8fe61db63", "generation_seconds_batch": 21.946329755010083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2398197650909424, "target_z": 1.2656251142491652, "ce": 6.3641486167907715, "genuineness": 4.557555198669434, "identity": 0.48862364888191223, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/349235d48e88e8eacab5553edbaf5887beb0f27569d17cdb5939e42614cf98bb.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "352dc78ccf9540639eab3a00e9e9ecc1d4e7c0301ffcfd469654a48f181715a1", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7b6dcf32fe4a676ba553f373f8e73a09dce74dd23dd24594bdaa09256924f318", "generation_seconds_batch": 21.654154394054785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12214800715446472, "target_z": -0.492187513182596, "ce": 6.046441555023193, "genuineness": 4.356721878051758, "identity": 0.5485110878944397, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/352dc78ccf9540639eab3a00e9e9ecc1d4e7c0301ffcfd469654a48f181715a1.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "355c41197616a34c0d06e430f11065b19a015b04b3d65994e0b681b0beb9f92f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "081bb7c07135baf9f08392a1630c03d6db2749ed239887e5f3b81bdce66176a1", "generation_seconds_batch": 24.537110147066414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3571695387363434, "target_z": -0.12255858322223237, "ce": 6.23706579208374, "genuineness": 4.494794845581055, "identity": 0.5768325924873352, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/355c41197616a34c0d06e430f11065b19a015b04b3d65994e0b681b0beb9f92f.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "35da07d032560afec769c568547d5df6ee11a5165346b13957e2afa5516346ca", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a9c234fcf9ecf5950ebca1c99c133c7144e8a378619e4b9556dcb51cd433026e", "generation_seconds_batch": 22.28079798608087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8855855464935303, "target_z": 2.2812499941410684, "ce": 5.744620323181152, "genuineness": 4.595211505889893, "identity": 0.7404708862304688, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/35da07d032560afec769c568547d5df6ee11a5165346b13957e2afa5516346ca.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "36476e96395fa5441059c3751b04f8eb25b2528900bf665eabcf34e8f3774d18", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8e89482b01d1fbb6c679d3b958239653aa9fbe0428db3ed6a5382cd8626c8ba7", "generation_seconds_batch": 22.870538763003424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4732887744903564, "target_z": 1.6328123227673206, "ce": 6.292664527893066, "genuineness": 4.65797233581543, "identity": 0.359333872795105, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/36476e96395fa5441059c3751b04f8eb25b2528900bf665eabcf34e8f3774d18.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "36d28f663dbf4f4a3b70ae4f6a71dd7229be72305ef37f4e5ffc14018f84185c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "264765ded2f1a71f735fe56828987c9fefd08ae388295824cd87d4b60f084775", "generation_seconds_batch": 25.124030200997368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6623560190200806, "target_z": 0.3574219163787041, "ce": 5.990842819213867, "genuineness": 4.7458367347717285, "identity": 0.45238184928894043, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/36d28f663dbf4f4a3b70ae4f6a71dd7229be72305ef37f4e5ffc14018f84185c.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "36f95ff3149d1c8f3251e5ee0362f5170599df8571dc407368cbb44cf74676b4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a375cd0991bcf3aa90c1c14fb354fb9219c5001d436041a2631b9079220bb789", "generation_seconds_batch": 16.421415170072578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1752431392669678, "target_z": 1.164062551265651, "ce": 5.95112943649292, "genuineness": 4.369274139404297, "identity": 0.6875578761100769, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/36f95ff3149d1c8f3251e5ee0362f5170599df8571dc407368cbb44cf74676b4.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "36fefa0b445ff9cff8f43cac6b1e318e2f27ef438350ffcae9b839020b845c85", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5ca2ec1ddb2a4addbaeb958e7af5b6fff21ba17b77500dcae09ebcd320886b3", "generation_seconds_batch": 18.84497840795666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.094217538833618, "target_z": 2.609374909186561, "ce": 5.847874641418457, "genuineness": 4.532451152801514, "identity": 0.7428191900253296, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/36fefa0b445ff9cff8f43cac6b1e318e2f27ef438350ffcae9b839020b845c85.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "3717ca2335d26111042c00b360a32a31e647522fd6226ebe792f1a23b9a572c9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d08e3b1716da9ce90f9af2b75ca1db789ed55bf0251c52b11bc064c223fbb793", "generation_seconds_batch": 22.018306251964532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4484517574310303, "target_z": 1.5937500292946578, "ce": 6.395919322967529, "genuineness": 4.507347106933594, "identity": 0.3906604051589966, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3717ca2335d26111042c00b360a32a31e647522fd6226ebe792f1a23b9a572c9.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "373a721f626e55ce3cb0198532afd36f27828a1da5696bdef70018a0b2e5c98c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bf724c7eb1a802ae7037720327cb3645ab5e37023fa1dd7af06e74eb0df3b71e", "generation_seconds_batch": 23.43637649808079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8126207590103149, "target_z": 0.5937500292946578, "ce": 5.847874641418457, "genuineness": 4.7834930419921875, "identity": 0.6292744278907776, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/373a721f626e55ce3cb0198532afd36f27828a1da5696bdef70018a0b2e5c98c.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": "374a2ac98fb61b6de7248b659ff95ff622753a5c6033ceb6badca173c4ab15ea", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "351f76a21c2209df58e82545c25ec4c07121cf6cbf3642dee38514c36a4b3e2f", "generation_seconds_batch": 19.03680490399711, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0485737323760986, "target_z": 0.9648438796288606, "ce": 5.649308204650879, "genuineness": 4.7081804275512695, "identity": 0.6789047122001648, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue elle était ici près de la grande bibliothèque Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/374a2ac98fb61b6de7248b659ff95ff622753a5c6033ceb6badca173c4ab15ea.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "37dc9955b54e8b14da7c282e9ce5ec8b1dddb35f19ee28772661f28399374e4c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "877ea988d728e1c4574978adfa742fd1989d1f268b1709d3a6ce888512cd32fd", "generation_seconds_batch": 24.72701564594172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6868884563446045, "target_z": 1.9687501464732888, "ce": 6.165581703186035, "genuineness": 4.425758361816406, "identity": 0.6278067231178284, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/37dc9955b54e8b14da7c282e9ce5ec8b1dddb35f19ee28772661f28399374e4c.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "37f2b6f6759bfe4382510c29dafb895b3ea85d126303132f5be5ce675b8f1220", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "939ff2f40f6da7c54f63b37bfc31eedf132876a120f7c50b66bdea91d1d3a4dd", "generation_seconds_batch": 16.595432532019913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4388216435909271, "target_z": 0.005859353395189902, "ce": 5.855817794799805, "genuineness": 4.570107460021973, "identity": 0.4806586503982544, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/37f2b6f6759bfe4382510c29dafb895b3ea85d126303132f5be5ce675b8f1220.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": "38c7d59b7595ecdd06a80ed257be1cd0dc0942d3f39fe1f17d89b27c754885b7", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ac86c6dd657c388be452616f3cd4f6b9aeb351d3cffbadb11ff56bd3d57c0c32", "generation_seconds_batch": 19.942509043961763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.839332103729248, "target_z": 3.7812500878839734, "ce": 5.617537498474121, "genuineness": 4.582659721374512, "identity": 0.5222587585449219, "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_Longing/38c7d59b7595ecdd06a80ed257be1cd0dc0942d3f39fe1f17d89b27c754885b7.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "3940d6730b37e166113de5a9da063ba9d3a1f3f566d80e1ac97c50df8a76a8c0", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59c5eff5a1b0ace0a70ed5c126accf1ad69f1a6fe5b71d23a407412690af1753", "generation_seconds_batch": 25.125808184035122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.315877765417099, "target_z": -0.1875000117178631, "ce": 6.205295085906982, "genuineness": 4.469690799713135, "identity": 0.19449225068092346, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3940d6730b37e166113de5a9da063ba9d3a1f3f566d80e1ac97c50df8a76a8c0.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": "394b6ac8c4e7a6e640d92f45a9471c5c7b58125867a88b4abe72ba8dcc5a804e", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ef48c6eef091b0b015914ccbd7f6945582d7c1ca45972b5981cfb3ab8ff60f3", "generation_seconds_batch": 16.619256684090942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8359112739562988, "target_z": 2.2031250322241234, "ce": 6.141753673553467, "genuineness": 4.369274139404297, "identity": 0.3154170513153076, "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_Longing/394b6ac8c4e7a6e640d92f45a9471c5c7b58125867a88b4abe72ba8dcc5a804e.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "39a8d533cd09037f2421ae6840c05a9aae3e1746a1dbc136a98baed2a3461c72", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d6daacf614e520c106da0b608e53f14d78d549032cbc05e9ed0ecb8e7b3683f", "generation_seconds_batch": 22.751727318041958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2398197650909424, "target_z": 1.2656251142491652, "ce": 5.990842819213867, "genuineness": 4.381826400756836, "identity": 0.5504385828971863, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/39a8d533cd09037f2421ae6840c05a9aae3e1746a1dbc136a98baed2a3461c72.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "3a1f87e612f3cfbdbc29fb0e98132de813f9b28c60dc03aff2594a14c175ee9a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d874e6fb2c968ea6e09db76b76a8a58a5511f274130ad2f2bdf558a531bf8129", "generation_seconds_batch": 23.985028589027934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6074094772338867, "target_z": 1.8437499824232053, "ce": 6.23706579208374, "genuineness": 4.369274139404297, "identity": 0.5867986083030701, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3a1f87e612f3cfbdbc29fb0e98132de813f9b28c60dc03aff2594a14c175ee9a.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "3a38d535cd1fd9b605fc18d84c7b58775b46de744a16ed9957b9eeaa5cf59940", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "69fd463e5bc91f5f2900f0eb42afa492e1af21c7be4694b0fdcd5d0297f7146c", "generation_seconds_batch": 25.4729586369358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1206014156341553, "target_z": 1.0781250556598498, "ce": 6.316492557525635, "genuineness": 4.570107460021973, "identity": 0.6481372117996216, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3a38d535cd1fd9b605fc18d84c7b58775b46de744a16ed9957b9eeaa5cf59940.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "3b0ccc6c6c9bf6778cc1f1f0bb98ea7d28a1ebde2338925c29f6f2b7bf510467", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9592290d87ed4e5a1f5f52052c9403a5b2a319aa42fedc9b9c79a7b77517e3ce", "generation_seconds_batch": 24.64933230704628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5925071239471436, "target_z": 1.820312381356636, "ce": 5.661221981048584, "genuineness": 4.720732688903809, "identity": 0.6173945665359497, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3b0ccc6c6c9bf6778cc1f1f0bb98ea7d28a1ebde2338925c29f6f2b7bf510467.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "3b2d9db89860d4157bf0b670dab034c6316b52c170411e4e3ceef1335b2b46ec", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d84e43d8871ec9da378a47e6f9fe1d6dbd32e4e2a5513cd533fce3fe0786c6c", "generation_seconds_batch": 17.39469522202853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.433549404144287, "target_z": 1.5703124282280885, "ce": 5.6334228515625, "genuineness": 4.65797233581543, "identity": 0.5992336869239807, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3b2d9db89860d4157bf0b670dab034c6316b52c170411e4e3ceef1335b2b46ec.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "3b8d1e2ccb5d07f09a5c85d2a36cfc0b6f8e31a36777cff235b25b7d54f6c1e0", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "34c651455e24f93ee23191892f92f4f746bd95ba5a9b2bc8e2697a03cebfe362", "generation_seconds_batch": 19.458215913036838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5692166686058044, "target_z": 0.21093747217007514, "ce": 6.09409761428833, "genuineness": 4.369274139404297, "identity": 0.5955584645271301, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3b8d1e2ccb5d07f09a5c85d2a36cfc0b6f8e31a36777cff235b25b7d54f6c1e0.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "3bc7c2e7d1a7fb2d8a160b51e97d8d7a82ea20616e724e3d68e8c05199e3c54c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "09efbb0a1058e337f8150f0d7aeb2fad1be1428cf598e7ea34b3d52c0974f818", "generation_seconds_batch": 25.037237051990815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.637214183807373, "target_z": 1.890625184556344, "ce": 5.609594821929932, "genuineness": 4.557555198669434, "identity": 0.6670932173728943, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3bc7c2e7d1a7fb2d8a160b51e97d8d7a82ea20616e724e3d68e8c05199e3c54c.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "3be35159908851f8fc6af90433028a12f194d3f3638b3b0779fb16edfac5c063", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e0bc88e151c099c9c24302b983855c284734a282e59badf038fc52f1d15f9e32", "generation_seconds_batch": 24.885752550093457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0287039279937744, "target_z": 0.9335937448734349, "ce": 5.871703147888184, "genuineness": 4.444586753845215, "identity": 0.27744969725608826, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3be35159908851f8fc6af90433028a12f194d3f3638b3b0779fb16edfac5c063.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "3c1720c74d46d442e21f9e2f4af48f6988958eb48732644eec86909022ba6044", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a61903238e76a29391f2f99a0f09f55e26ef4fb8f18a16dee7d161bd4d57b4f8", "generation_seconds_batch": 26.29509677097667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2348523139953613, "target_z": 1.2578125805603089, "ce": 6.086154937744141, "genuineness": 4.457139015197754, "identity": 0.5727091431617737, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3c1720c74d46d442e21f9e2f4af48f6988958eb48732644eec86909022ba6044.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": "3c2b329fe00deacf87f5e8a79f674215d12ac1a68f14cd8165458742ce683ac2", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "33b25c4be4e2fc32f4d2e74110bf4f3465f0408a7014abfd3301853c4c076655", "generation_seconds_batch": 22.86511001805775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7896575927734375, "target_z": 3.703124750995409, "ce": 5.085378646850586, "genuineness": 4.243753433227539, "identity": 0.4246962070465088, "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_Longing/3c2b329fe00deacf87f5e8a79f674215d12ac1a68f14cd8165458742ce683ac2.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "0098c6e871bed99dcd1527f12f0be9a98bc82a25619e410c342177147d8a8d40", "generation_seconds_batch": 19.28716493700631, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0426691472530365, "target_z": -0.6171874897468698, "ce": 6.141753673553467, "genuineness": 4.268857479095459, "identity": 0.6504290103912354, "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_Longing/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": "3cca2b838aa3adc82dca9f26acbb920e01bb0f4c61dd6533fa58d97928917b48", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a5d02cc142c44ed77dbfd53982feb9be9ded26548252a9bd06589e5f570b676", "generation_seconds_batch": 25.55105175601784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8324904441833496, "target_z": 0.6249999765642738, "ce": 6.046441555023193, "genuineness": 4.419482707977295, "identity": 0.3112565875053406, "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_Longing/3cca2b838aa3adc82dca9f26acbb920e01bb0f4c61dd6533fa58d97928917b48.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "3d2eab3d91d62c1641d8ac8d2cbcee7f3e5072ca6a9801b91232681ba7cb515f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6b9d56ae4d7868ec5791a9e4f8443b9e2056fc9f4992703f7fc2f21016728f02", "generation_seconds_batch": 26.902615499100648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7927510142326355, "target_z": 0.5624999882821369, "ce": 5.903473377227783, "genuineness": 4.193545341491699, "identity": 0.5967139005661011, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3d2eab3d91d62c1641d8ac8d2cbcee7f3e5072ca6a9801b91232681ba7cb515f.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "3d7f03f5d3e19164d96a5b3503743520e069beb5f0c67c9c9e315931c9a4613f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a7c2151b0469f15dab1ef6cfeb2ef6953c2b74468ecf22b98a4347b0cc0ee3d6", "generation_seconds_batch": 26.25543559109792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8300067186355591, "target_z": 0.6210937097198456, "ce": 5.982900142669678, "genuineness": 4.469690799713135, "identity": 0.7938905954360962, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3d7f03f5d3e19164d96a5b3503743520e069beb5f0c67c9c9e315931c9a4613f.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "3daab7cebf5cb90077a0c49c8fc5a61d7a4e435480ce57e0a42b40249e7fdc79", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2ebf2fec93ca19236aae221f5cd6204b42b5433ffe3f6b434872772f9e832953", "generation_seconds_batch": 24.92062608303968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.210015058517456, "target_z": 1.2187499121160268, "ce": 5.704906940460205, "genuineness": 4.413206577301025, "identity": 0.5124720335006714, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3daab7cebf5cb90077a0c49c8fc5a61d7a4e435480ce57e0a42b40249e7fdc79.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "3dcc02f8f5768bbd67938f0d92f2a49909c5c6140b0c787159d04da6f0b81637", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "75fabe959cba16289ffeabf39c0ac04402a34cc7d3d8e80c4f5c2867a3577a83", "generation_seconds_batch": 29.907475398969837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6561467051506042, "target_z": 0.34765624926763355, "ce": 6.070269584655762, "genuineness": 4.193545341491699, "identity": 0.46699750423431396, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3dcc02f8f5768bbd67938f0d92f2a49909c5c6140b0c787159d04da6f0b81637.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "3e398bee43b8ab5adc9344d48fbfa03f6123eec521612936a87cad86508c661b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f98e3e352913d2243d45ebe3dd3c6cbe073dbb93225b7dc7652e2585ac7ccc7", "generation_seconds_batch": 24.289808382978663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4683215618133545, "target_z": 1.6250001640500835, "ce": 5.80021858215332, "genuineness": 4.394378662109375, "identity": 0.31849369406700134, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3e398bee43b8ab5adc9344d48fbfa03f6123eec521612936a87cad86508c661b.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "3ea4117328ffd140adf021d601d7eb8332e1e506eb5ef626d9095fa1b74dda4f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "deea52b97b425ce8f70b423a4a9fddd6b329dc45bb8852fec9fea07512a23aa0", "generation_seconds_batch": 25.1199758190196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0659596920013428, "target_z": 0.9921875600540484, "ce": 6.086154937744141, "genuineness": 4.582659721374512, "identity": 0.6537653803825378, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3ea4117328ffd140adf021d601d7eb8332e1e506eb5ef626d9095fa1b74dda4f.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "3f352858b4448090c35e94916525709057b099968c239d1c0208cbc791f676fc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc906c606a1c45412f9ab03f9f32465f0c885ca902d1ccb0bdd718a0850db9a0", "generation_seconds_batch": 23.342831077985466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6673234105110168, "target_z": 0.3652343563246557, "ce": 5.959072113037109, "genuineness": 4.607763767242432, "identity": 0.6800982356071472, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/3f352858b4448090c35e94916525709057b099968c239d1c0208cbc791f676fc.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "40656ad145115a10823bafce31b488fdd979ed7bc79cd230e963b746efc45c2c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "73497dc18045cee354be79f0f68453c5e8a270862c1018ecfafb5e6566ba7d42", "generation_seconds_batch": 25.44910821702797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.205047607421875, "target_z": 1.2109373784271702, "ce": 5.446769714355469, "genuineness": 4.570107460021973, "identity": 0.5473537445068359, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/40656ad145115a10823bafce31b488fdd979ed7bc79cd230e963b746efc45c2c.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "40832dae6242c0d575ec490735eec622581eb6101d04d517e574984b042fd903", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b991d9e0f9050009e681d288ceef347f38927ab45ab96031870c9c7612cca75b", "generation_seconds_batch": 27.463138798018917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0898597240447998, "target_z": -0.5429687478029007, "ce": 6.173524379730225, "genuineness": 4.381826400756836, "identity": 0.737195611000061, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/40832dae6242c0d575ec490735eec622581eb6101d04d517e574984b042fd903.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "40d12db218fa2145370b9478a994cb9a83b4a563150da16ea46d5772c7dabda0", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "07cf77908bf9bb3371d68a5c03d45c894838a0a4f4349bd5143d8180e0705da1", "generation_seconds_batch": 26.20704464998562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6573885679244995, "target_z": 0.34960938268984765, "ce": 5.796247482299805, "genuineness": 4.319066047668457, "identity": 0.4261956810951233, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/40d12db218fa2145370b9478a994cb9a83b4a563150da16ea46d5772c7dabda0.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "418ab25282dca6a2a1a76af82d8d8b6d21f39df091dc5d2bf6862bfe6ca4de16", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "790e2868f6376f727d630d97add4c4d06dcd603d6f205855ba6f20cce14dada0", "generation_seconds_batch": 21.667178951087408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2724127769470215, "target_z": -0.2558593533951899, "ce": 6.205295085906982, "genuineness": 4.394378662109375, "identity": 0.7062592506408691, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen heen 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_Longing/418ab25282dca6a2a1a76af82d8d8b6d21f39df091dc5d2bf6862bfe6ca4de16.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "41fe2ad145be365ebac42b224753832b61df7854bd30b6de3911592d11d2d44e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3b1a71ae8c58a6eddcaae011708848dd618940b1b64cfd4b8cd1187c8b31e967", "generation_seconds_batch": 22.83506137493532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2333056926727295, "target_z": 2.828125102531302, "ce": 5.974957466125488, "genuineness": 4.607763767242432, "identity": 0.8281883001327515, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/41fe2ad145be365ebac42b224753832b61df7854bd30b6de3911592d11d2d44e.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "420e6604b2c87ee5309fdd948efaf01469796e0d508a3b88fb7253564efd0806", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "90002c185a967169d4d6232ef2899b1fd6f9281cd1933dcfe88c8537821aa5de", "generation_seconds_batch": 21.903917885036208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9914482235908508, "target_z": 0.8750000234357262, "ce": 5.80021858215332, "genuineness": 4.482243061065674, "identity": 0.5313692092895508, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/420e6604b2c87ee5309fdd948efaf01469796e0d508a3b88fb7253564efd0806.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "e0c16f8e17e0f542873879a1d8f806f8dcfe33e983f5bf0862bc951d42a91b42", "generation_seconds_batch": 17.892103416961618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005413413047790527, "target_z": -0.6757812580560308, "ce": 6.0146708488464355, "genuineness": 4.331617832183838, "identity": 0.6055152416229248, "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_Longing/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "4387f1d355023b031a09912dedbbe9790bb302f92d9e47c148f544bf3deee369", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7df5c54d72d05421f742734372d59e08f3e4b0009d1693685b4f9993305e4e29", "generation_seconds_batch": 20.42335507401731, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6769535541534424, "target_z": 1.9531250790955759, "ce": 5.871703147888184, "genuineness": 4.7458367347717285, "identity": 0.6989094018936157, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4387f1d355023b031a09912dedbbe9790bb302f92d9e47c148f544bf3deee369.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "438ee68a4a3291cb1878f0d5072471d6cab0d71e453098ea697b4810037ade2a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fae820f96527def54e859fff4b9cd36ec638772068dd934e9136ee8189507f05", "generation_seconds_batch": 18.343926599016413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2891778349876404, "target_z": -0.22949219280965671, "ce": 6.086154937744141, "genuineness": 4.6705241203308105, "identity": 0.7296315431594849, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/438ee68a4a3291cb1878f0d5072471d6cab0d71e453098ea697b4810037ade2a.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "4397e56df9297d2236aed1f15d6f7e805f0407769218910f6fbee1891d90b10e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b1a4adfe7b38bc747998183138e4f2cc6b9cda77e58381817eabeed43f5a5bb3", "generation_seconds_batch": 24.838693060097285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18299901485443115, "target_z": -0.39648439733717655, "ce": 6.133810997009277, "genuineness": 4.444586753845215, "identity": 0.708939790725708, "hypothesis": "ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4397e56df9297d2236aed1f15d6f7e805f0407769218910f6fbee1891d90b10e.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "43822319e4a763b1256d067b2bbe05928d6f08b7c4cc0dd7e625ba37a10eb56f", "generation_seconds_batch": 17.983043245971203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3494079113006592, "target_z": -0.13476564367534433, "ce": 6.23706579208374, "genuineness": 4.595211505889893, "identity": 0.6945444345474243, "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_Longing/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "444403d6ea3ec50628748318a72c669aee03d42f1f7ba344e32bffec4572c13f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "943fafe704caa8b2c4dd3a1fbb9ad104e9aa1950e30c7e71c631fc706feaf67f", "generation_seconds_batch": 20.807731081964448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6670186519622803, "target_z": 1.9375000117178631, "ce": 6.229123115539551, "genuineness": 4.68307638168335, "identity": 0.40789172053337097, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/444403d6ea3ec50628748318a72c669aee03d42f1f7ba344e32bffec4572c13f.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "446c7e43ddab95ba8799405bc098212decdc9d070f502563b9d8bcf7e393feda", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d9800ea836cecefbd428db8a1f7d286b0cf463c395a9529b05b2dd0a21a29454", "generation_seconds_batch": 25.47311564499978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6772582530975342, "target_z": 0.3808593299594637, "ce": 6.38003396987915, "genuineness": 4.381826400756836, "identity": 0.42208266258239746, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/446c7e43ddab95ba8799405bc098212decdc9d070f502563b9d8bcf7e393feda.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "457f65e358bc4a912010a754363b2966a3314618f0d8a54c144c0db886adc12a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b652e93439e29e04a41a8d08011cd0ebd9bb3c1b5dd4d232b6cc1358115b2ff9", "generation_seconds_batch": 22.389436692930758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2944614887237549, "target_z": 1.3515626098549667, "ce": 6.078212261199951, "genuineness": 4.469690799713135, "identity": 0.5673455595970154, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/457f65e358bc4a912010a754363b2966a3314618f0d8a54c144c0db886adc12a.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "e2ebf6648b9a5c5f27f006c222519d2cea8d968b5ba970a5320d01c93f9c1ee9", "generation_seconds_batch": 16.78777427400928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007005155086517334, "target_z": -0.6953124985352671, "ce": 6.41180419921875, "genuineness": 4.143336772918701, "identity": 0.4405162036418915, "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_Longing/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "46160d91d77c666d2f5f3940ffb18cca81bb21792e1c6d0dd7721339ed89e3de", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2648a30d076f0c5c10f55a4bbe7fd346b6ccb253da26f88827ac348ed4b78c28", "generation_seconds_batch": 18.236051713931374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4583866596221924, "target_z": 1.6093750966723706, "ce": 5.780362129211426, "genuineness": 4.13078498840332, "identity": 0.36213189363479614, "hypothesis": "The door is still open. I've 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_Longing/46160d91d77c666d2f5f3940ffb18cca81bb21792e1c6d0dd7721339ed89e3de.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "463d0015e5d489a2b386c4ada29623b01cc96a2666513f09092e108a1d39bce6", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e6e600ce042890cac52a6061f29a2ec74599e7597820036bb01f46f6d256f678", "generation_seconds_batch": 18.691605882020667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23639890551567078, "target_z": -0.3124999882821369, "ce": 6.0305562019348145, "genuineness": 4.519899368286133, "identity": 0.5341636538505554, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/463d0015e5d489a2b386c4ada29623b01cc96a2666513f09092e108a1d39bce6.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "466d2ae8f81dd6fcd380dbd7f90ca8b0e73d5945ecffc0e4576375587b508740", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e94066d2dd45ad3fe77d018df0b70b69f6031ada290cd986fb9b6b7811cb38ff", "generation_seconds_batch": 25.47311564499978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7877836227416992, "target_z": 0.5546875483361853, "ce": 6.499174118041992, "genuineness": 4.494794845581055, "identity": 0.6979769468307495, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/466d2ae8f81dd6fcd380dbd7f90ca8b0e73d5945ecffc0e4576375587b508740.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "46bd78d3dacebf53ea8187af8ffdc1de7e96db0ff2d0a772659b80f49bef6098", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0fd5e6d30e46a84c3c7e16f74ba15a254c74f6cbaeda247459636d9d4c90e09e", "generation_seconds_batch": 23.11505231098272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.627279281616211, "target_z": 1.875000117178631, "ce": 5.967014789581299, "genuineness": 4.507347106933594, "identity": 0.5261213183403015, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/46bd78d3dacebf53ea8187af8ffdc1de7e96db0ff2d0a772659b80f49bef6098.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "470639c4cfa194a741be8512e78d447df4710e6f20aa3195c783b8fb3afdb74e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6d90bbdde20e26507994312436729f7056404462ee37bacf7ef848a5a6c2a8a6", "generation_seconds_batch": 22.19163362006657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3491032123565674, "target_z": 1.437500105460768, "ce": 5.911416053771973, "genuineness": 4.406930446624756, "identity": 0.7575515508651733, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/470639c4cfa194a741be8512e78d447df4710e6f20aa3195c783b8fb3afdb74e.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": "477b5e12f0b87f04c01a0efc4128928d97b68c103f5fbc0464bec78792535b01", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bacb6c3ce301170deba2d4999c62db55b42453c740e41b42c91eab55d36197c0", "generation_seconds_batch": 24.594738894957118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0038667917251587, "target_z": 0.8945312639149624, "ce": 5.704906940460205, "genuineness": 4.545003414154053, "identity": 0.7526382207870483, "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_Longing/477b5e12f0b87f04c01a0efc4128928d97b68c103f5fbc0464bec78792535b01.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "479ad60d82d0deeaf59872af81cc7fe30ee153d0825a2b68b33645f756ff2cff", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "23de758d8145cd972ab629693d66e6a9463d55da6e9e79e9e57133958cc7d8ac", "generation_seconds_batch": 27.49970280996058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4136797189712524, "target_z": 1.5390624809584725, "ce": 5.546053409576416, "genuineness": 4.256305694580078, "identity": 0.5620744228363037, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/479ad60d82d0deeaf59872af81cc7fe30ee153d0825a2b68b33645f756ff2cff.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "d304f44a00bc79a8d5045530c5641fac60e78ea62798e0ba9b951c2a5563ea55", "generation_seconds_batch": 18.3529529790394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15319445729255676, "target_z": -0.443359365113053, "ce": 6.070269584655762, "genuineness": 4.457139015197754, "identity": 0.7852122783660889, "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_Longing/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "4828aed7f8068a2e740d7572ee745d495eb4008f8e1f9e6cc92ed0ea42d07f69", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a0c4c579ed497f49f7fb48b9dcd6354e07259196990175941018e2ed20fdc2fd", "generation_seconds_batch": 21.88683728396427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.319298505783081, "target_z": 1.3906249033276294, "ce": 6.300607204437256, "genuineness": 4.507347106933594, "identity": 0.6203481554985046, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4828aed7f8068a2e740d7572ee745d495eb4008f8e1f9e6cc92ed0ea42d07f69.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "48ec602e86f5979d030e132a55b79f2b473166c4f44fa083fc0158ed3635d0ee", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "a1e5a84d5ec6f7a3f70f93cc96475392c259949300d7a9591c253d4eec92b496", "generation_seconds_batch": 16.77577744598966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2696242332458496, "target_z": 1.3124999414106844, "ce": 5.665193557739258, "genuineness": 4.482243061065674, "identity": 0.7090467214584351, "hypothesis": "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_Longing/48ec602e86f5979d030e132a55b79f2b473166c4f44fa083fc0158ed3635d0ee.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "49cdb9348ae7574407bc1038b7edf20675ccc783261126bc6f3094c6bae3b86c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bc1b0c45ecb90af2a635fbd62e9553d5efaa1ab7803fb8184ad5df11549669db", "generation_seconds_batch": 23.727141625946388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0758945941925049, "target_z": 1.0078126274317614, "ce": 5.665193557739258, "genuineness": 4.607763767242432, "identity": 0.6525444388389587, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/49cdb9348ae7574407bc1038b7edf20675ccc783261126bc6f3094c6bae3b86c.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b3958cd65f0b2f71c14defdc58cf2f3c9dc86ab0f4f6d2fb9dbd8d0a5bfbc029", "generation_seconds_batch": 19.844086594996043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4782562255859375, "target_z": 1.640624856456177, "ce": 6.173524379730225, "genuineness": 4.268857479095459, "identity": 0.6538039445877075, "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_Longing/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "4a0ee0ca4f89b302b130c0f70fcd7e7fd3680d2950d24f42495c8a917e435d06", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a2a806257ef91b44511490d1ae25b9299183081d7eb8488572c35f114dea175c", "generation_seconds_batch": 25.98875965597108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4633541107177734, "target_z": 1.617187630361227, "ce": 6.284721851348877, "genuineness": 4.494794845581055, "identity": 0.44732019305229187, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4a0ee0ca4f89b302b130c0f70fcd7e7fd3680d2950d24f42495c8a917e435d06.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "4a8e76dce2867c13502271383c171e6c698b69662f96ca09dbdda7a657869566", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1823288c0aabc46eff47f60d0ed2e64a116ca699f4229f719810f5cb81b93638", "generation_seconds_batch": 24.885752550093457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7753649950027466, "target_z": 0.5351562141140442, "ce": 5.696964263916016, "genuineness": 4.231201171875, "identity": 0.5851006507873535, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4a8e76dce2867c13502271383c171e6c698b69662f96ca09dbdda7a657869566.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "4b3334cb5afacb4e3f04b7fa38efc6bb3dce8724779dd5dd41ec583195d07bd6", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "20955a97dae2c9ce309a035e6044e9563d6ecd8eeb11b5e8aab098a04f0ddf13", "generation_seconds_batch": 22.048509799991734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4434843063354492, "target_z": 1.5859374956058014, "ce": 5.450741291046143, "genuineness": 4.218649387359619, "identity": 0.34053587913513184, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4b3334cb5afacb4e3f04b7fa38efc6bb3dce8724779dd5dd41ec583195d07bd6.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": "4b5551bca19e1b3c65ace04184a89d8c6b03ab32fa28b5cb721fe6085558aad6", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96440d9552197d37fb6507f3841baed371e94c1375fe578133f9df45ca9bfadf", "generation_seconds_batch": 22.823023890028708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5356865525245667, "target_z": 0.15820315099900875, "ce": 6.022613525390625, "genuineness": 4.557555198669434, "identity": 0.7684858441352844, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lese genau, und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4b5551bca19e1b3c65ace04184a89d8c6b03ab32fa28b5cb721fe6085558aad6.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "4bf19ead4fbde84b3569353d7d5189a2b8830e39904cd23f8e588c497715a853", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d6fe1ae7ef2ce10d8bfe601306cd2293bb6751a4c5a6e71396f35d3983af665f", "generation_seconds_batch": 24.80073210899718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2631101608276367, "target_z": 2.8749999296928213, "ce": 5.935244083404541, "genuineness": 4.7081804275512695, "identity": 0.8182806968688965, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4bf19ead4fbde84b3569353d7d5189a2b8830e39904cd23f8e588c497715a853.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": "4c22143f1de627e9338cc9163bc68b791198a36df932d1a2d835b45a15325ef7", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4851a44564495f883ef625553f1502772dde7db9aa6545803b513323111d7ada", "generation_seconds_batch": 20.75620990805328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4683215618133545, "target_z": 1.6250001640500835, "ce": 6.109982967376709, "genuineness": 4.457139015197754, "identity": 0.3984798192977905, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4c22143f1de627e9338cc9163bc68b791198a36df932d1a2d835b45a15325ef7.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "4c276b69880306fd9341640d2e1830d81508a3abd48344e1b07647f5bf851245", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d30cac41844146bef815add63e1966056c481b323ee577101c8092ed7220dd75", "generation_seconds_batch": 19.884153173072264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2646567821502686, "target_z": 1.304687407721828, "ce": 6.205295085906982, "genuineness": 4.7834930419921875, "identity": 0.6277140378952026, "hypothesis": "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_Longing/4c276b69880306fd9341640d2e1830d81508a3abd48344e1b07647f5bf851245.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": "4c32a97046195ee29a471b70f183ef3cf5522037b49956b113d727283a68979d", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "43051da4427302c6f8bd40fa28f06e89eb082dc82e011f4ff5e8fff528232f45", "generation_seconds_batch": 18.275159658980556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5527677536010742, "target_z": 1.757812486817404, "ce": 5.804190158843994, "genuineness": 4.632867813110352, "identity": 0.7559635639190674, "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_Longing/4c32a97046195ee29a471b70f183ef3cf5522037b49956b113d727283a68979d.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "4d3eb47991439dc7255f8751341f2ec658c729beb5e33cf4b44148c4a1fd0652", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1cecab8c465753ab29c46114049403275d579830dae9da2265a91bc1d1457c4d", "generation_seconds_batch": 19.31731666205451, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0411224365234375, "target_z": 0.9531248916097663, "ce": 5.903473377227783, "genuineness": 4.607763767242432, "identity": 0.49470141530036926, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4d3eb47991439dc7255f8751341f2ec658c729beb5e33cf4b44148c4a1fd0652.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "4d62823dd7836d860ec40dfa0fa217a973337cd149a5fa58b9d25ee7db09fc61", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b73e3367f01fe83d1b0bb67a6e28f9b71ef5afd676f9aa2e400a42590ada9be7", "generation_seconds_batch": 24.319857925060205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1702756881713867, "target_z": 1.1562500175767947, "ce": 6.133810997009277, "genuineness": 4.507347106933594, "identity": 0.7395303249359131, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4d62823dd7836d860ec40dfa0fa217a973337cd149a5fa58b9d25ee7db09fc61.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "4d86f8c8017663d4ff57e87d76681a6ba2d0faeeac107162bc4944bcafa6dc21", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e7d1e64241ea6d789f1e6f5ad0e4e5d043fd91eeed065271d726a665c3525e61", "generation_seconds_batch": 22.86704268702306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3938100337982178, "target_z": 1.5078125336888564, "ce": 6.022613525390625, "genuineness": 4.68307638168335, "identity": 0.23054343461990356, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4d86f8c8017663d4ff57e87d76681a6ba2d0faeeac107162bc4944bcafa6dc21.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "4e179728fa0d0081d6f0571be1646c46751c322edac1f6563ae465ad4f93ffe5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7ea3d69087851bc69082d848b53ac88d89cf030539021e1512f4d5c4b91711bf", "generation_seconds_batch": 23.474023555056192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.736562728881836, "target_z": 2.0468751083902337, "ce": 5.974957466125488, "genuineness": 4.65797233581543, "identity": 0.8356524705886841, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4e179728fa0d0081d6f0571be1646c46751c322edac1f6563ae465ad4f93ffe5.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "4eeb08ccf24eee8bb842f6fdffd232a3dcaa3ac8d04b50633fb6a7b5f2e0fb95", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e322e5ba92d5cd3fc5a82869bb8428f27928c8379b2c4483a342d0d342683695", "generation_seconds_batch": 25.105259974021465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2891778349876404, "target_z": -0.22949219280965671, "ce": 5.998785495758057, "genuineness": 4.256305694580078, "identity": 0.6797119379043579, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4eeb08ccf24eee8bb842f6fdffd232a3dcaa3ac8d04b50633fb6a7b5f2e0fb95.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "4f4f702b4bcec2d3fca6631b03795ce5f81d85dcf06e6353060dbe5db89f2dfc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "37a020fec98bf54cddf7819a26aabfcdc7d60aa43c7b9bc6f63d92ebfe2fb0b2", "generation_seconds_batch": 18.027537417947315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06502258777618408, "target_z": -0.5820312287613731, "ce": 6.284721851348877, "genuineness": 4.469690799713135, "identity": 0.6433937549591064, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4f4f702b4bcec2d3fca6631b03795ce5f81d85dcf06e6353060dbe5db89f2dfc.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "4fe900dac85829f60ddab25b55bb6e43ebea8faa3cae3321ed4ad441082324d3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6409b949b43707b9ed074ac7cbed02e884e37c3da0849a236d9e60d33ee55f79", "generation_seconds_batch": 24.8015517789172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0162854194641113, "target_z": 0.9140625981371034, "ce": 5.677107334136963, "genuineness": 4.432034492492676, "identity": 0.5905027389526367, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/4fe900dac85829f60ddab25b55bb6e43ebea8faa3cae3321ed4ad441082324d3.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "503fb16e43206882768c9942b25fc6063784ba95faaf1a2120462856e46a1425", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "12be9b2eea211cd13a0182f135cfd078a1595591442d6cbacc6ad7311e264adf", "generation_seconds_batch": 22.648169490974396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8359112739562988, "target_z": 2.2031250322241234, "ce": 5.557967185974121, "genuineness": 4.595211505889893, "identity": 0.6885230541229248, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/503fb16e43206882768c9942b25fc6063784ba95faaf1a2120462856e46a1425.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "51b3623adda9f38c75878c6312cae58b1838d471621a23d0b12c5e61bf1416c3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bc77ecf1d2e5bd3de8b436f1738d155809035848bd89d30d588cf2158dbe8526", "generation_seconds_batch": 22.940672132070176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.974999189376831, "target_z": 2.4218748505972454, "ce": 5.824047088623047, "genuineness": 4.444586753845215, "identity": 0.5719091296195984, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/51b3623adda9f38c75878c6312cae58b1838d471621a23d0b12c5e61bf1416c3.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "51b6fd27a6f5aa69514cf6654053a53e3eef08045d2c0cbee02549022343f84b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8dc000545152834768d5f466cc0ed1737dae80d91219e0cd123342ed3ba39026", "generation_seconds_batch": 25.39416087407153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3043962717056274, "target_z": 1.3671874897468699, "ce": 5.903473377227783, "genuineness": 4.256305694580078, "identity": 0.34779414534568787, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/51b6fd27a6f5aa69514cf6654053a53e3eef08045d2c0cbee02549022343f84b.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "51bb2fc62417e6d9794164652784a1a50027d3c2a5d596da8f90367b363dedab", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d94d4141a84262864486f20ebe3d8b8240b556209c75ddcf8b79c84526fd1551", "generation_seconds_batch": 18.073447249014862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8324904441833496, "target_z": 0.6249999765642738, "ce": 6.117925643920898, "genuineness": 4.193545341491699, "identity": 0.4591667950153351, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/51bb2fc62417e6d9794164652784a1a50027d3c2a5d596da8f90367b363dedab.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "52683780116bf79ca0447959b350f1c4400e57ed7317dae76ad6ff4fa0e93ab7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bf3914573c5054b70b7fd6059db714557de51415e015ccf3633041af176b133f", "generation_seconds_batch": 24.859617750975303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49780988693237305, "target_z": 0.09863281597874062, "ce": 5.629451274871826, "genuineness": 4.432034492492676, "identity": 0.6473638415336609, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/52683780116bf79ca0447959b350f1c4400e57ed7317dae76ad6ff4fa0e93ab7.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": "52bcc466fcfbccdc1366195474569dbb3afae0cb9901f4f634ed6c1f602a506f", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90e22fc3746981b747c923a220b747527ec6b856a2ae3fd323205e3ecfd3c01f", "generation_seconds_batch": 24.594738894957118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.14047110080719, "target_z": 1.1093750029294658, "ce": 5.645336627960205, "genuineness": 4.607763767242432, "identity": 0.6346099376678467, "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_Longing/52bcc466fcfbccdc1366195474569dbb3afae0cb9901f4f634ed6c1f602a506f.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "5338b18c94ceb2726e0b038d0c370ac75f8b7297328f4e5101c357eefca71e7f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4ac23e614978b5e2361eee1a78a09bbbc8e51a6dae066eb5d9b4d57ce8e3ca48", "generation_seconds_batch": 23.41422524303198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18920831382274628, "target_z": -0.3867187536618322, "ce": 6.09409761428833, "genuineness": 4.482243061065674, "identity": 0.6039105653762817, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5338b18c94ceb2726e0b038d0c370ac75f8b7297328f4e5101c357eefca71e7f.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "53d5ceb8502b9cebc00373abdf37c919e659b9c9ae544899ff48da3302efa4cf", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bc7026f7de59c70b1e731456417f867066a64f893fb2d230061b9646b8d156c1", "generation_seconds_batch": 18.163537963991985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2531752586364746, "target_z": 2.8593748623151085, "ce": 5.855817794799805, "genuineness": 4.6956281661987305, "identity": 0.7647358775138855, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/53d5ceb8502b9cebc00373abdf37c919e659b9c9ae544899ff48da3302efa4cf.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "542972241d9fbcd666236cf7c6c271bb6ae25a682a51a0f0b4407b8f7591d5d3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b591af858bb7f6a5165ea2e4fe10c050c444d4f092a5acfdf7845656cd40632b", "generation_seconds_batch": 24.26889091404155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.956676185131073, "target_z": 0.8203124750995409, "ce": 6.23706579208374, "genuineness": 3.973883628845215, "identity": 0.37002789974212646, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/542972241d9fbcd666236cf7c6c271bb6ae25a682a51a0f0b4407b8f7591d5d3.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "1b3518b58f8b37e5f737db72e6c5d6de54074e8c58529307d5fd9b08e1f2845a", "generation_seconds_batch": 16.78777427400928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04922831058502197, "target_z": -0.7617187536618322, "ce": 6.284721851348877, "genuineness": 4.011539936065674, "identity": 0.5163894891738892, "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_Longing/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "5490ba47f083887a91c25f27de4cb8e03b8febd389f1a5013cda1da46053a165", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fa97456bfb93f6b323f58575867b5be5bff8f91a710d84aec5b526bdc5c39d38", "generation_seconds_batch": 25.627055373042822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3556172251701355, "target_z": -0.1249999765642738, "ce": 6.213237762451172, "genuineness": 4.582659721374512, "identity": 0.6526855230331421, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5490ba47f083887a91c25f27de4cb8e03b8febd389f1a5013cda1da46053a165.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": "54a0668eb984151a7ed0570f8645da13bc911d550642cf3419edbe5e72017ab5", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ea306a42c9a1cb403d82803cc1fec516ad41752d3c6c10446319316334e5be1", "generation_seconds_batch": 21.082567891920917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.537865400314331, "target_z": 1.7343748857508348, "ce": 5.80021858215332, "genuineness": 4.7081804275512695, "identity": 0.5904551148414612, "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_Longing/54a0668eb984151a7ed0570f8645da13bc911d550642cf3419edbe5e72017ab5.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": "54b3eac8b32322f21e331646facf7d21f5902d4b20f33494bad133cf74048f9d", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2ffaf344fc2045baaeb4ddad0857db3b17dbf96a54fbe4279f1addc17d1dc18", "generation_seconds_batch": 24.923399116960354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1255688667297363, "target_z": 1.0859375893487062, "ce": 5.597680568695068, "genuineness": 4.482243061065674, "identity": 0.525714635848999, "hypothesis": "Die Straße führt h der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "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_Longing/54b3eac8b32322f21e331646facf7d21f5902d4b20f33494bad133cf74048f9d.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "54e40eb3ffc637eefa280808414f97ca0b1f6936527e3c56ac32383f3341f005", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "98232a5d201d5e3e8114b439a197beecb58bdac4bf11c0c95dd59a54d29eefc9", "generation_seconds_batch": 18.36334352393169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05508771538734436, "target_z": -0.5976562492676336, "ce": 6.109982967376709, "genuineness": 4.218649387359619, "identity": 0.791117787361145, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/54e40eb3ffc637eefa280808414f97ca0b1f6936527e3c56ac32383f3341f005.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "5613999e16cb59c771cac699c57bc14f540a70dadb93e568919a293028242dcc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "13feaa6d1f29b216f4ff6a43b4a7e8d70a4fa4a834a1e4374fb5102c74a9de36", "generation_seconds_batch": 23.98390544799622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0709271430969238, "target_z": 1.0000000937429048, "ce": 6.070269584655762, "genuineness": 4.519899368286133, "identity": 0.79008948802948, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5613999e16cb59c771cac699c57bc14f540a70dadb93e568919a293028242dcc.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "57a816fe2019739a93afd0102d4c998d7f04b147633411a7abf0dda2a528bda4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "61c370ffad782c573a0583550fec90a73bdb679e7264e4975764e7f125a16c6b", "generation_seconds_batch": 23.961267848033458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8573275804519653, "target_z": 0.6640624575227463, "ce": 6.109982967376709, "genuineness": 4.770940780639648, "identity": 0.6436230540275574, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/57a816fe2019739a93afd0102d4c998d7f04b147633411a7abf0dda2a528bda4.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "57e9fdeacec562a5bef21c55190f91605f666eb76105ee8f9a138e15c70644ef", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "57cc4e7827eca7921943fbc1ad90a7dc15c7cae913f791eab7d87f14e4531e21", "generation_seconds_batch": 23.507680029957555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6449699997901917, "target_z": 0.33007814221061144, "ce": 5.911416053771973, "genuineness": 4.607763767242432, "identity": 0.6899808645248413, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/57e9fdeacec562a5bef21c55190f91605f666eb76105ee8f9a138e15c70644ef.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "5883da1f0b9851639b4bcd5b860a9f73603649a10941295bd6b8b65be4d2e55b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ae83995bdf3bf0535796299f9606076f0d34e45010a3a2ad50075286dc48abe0", "generation_seconds_batch": 17.76751710800454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21280360221862793, "target_z": -0.34960938268984765, "ce": 5.903473377227783, "genuineness": 4.425758361816406, "identity": 0.559926450252533, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen ze 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_Longing/5883da1f0b9851639b4bcd5b860a9f73603649a10941295bd6b8b65be4d2e55b.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "594e54e7177fabff3b9d4da34dabe61025b82834d048a13c94617e5dc60e6f3b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "76fa846f16ea701edfab352c1d06884fc22eb389dbc32571c429b385f8094974", "generation_seconds_batch": 15.359590281965211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.324265956878662, "target_z": 1.3984374370164858, "ce": 5.055593490600586, "genuineness": 4.099404335021973, "identity": 0.5710809826850891, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/594e54e7177fabff3b9d4da34dabe61025b82834d048a13c94617e5dc60e6f3b.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "59c0414da5693081080d9fd8553695cc1a16c61954abf3c01d31cd57a2f92451", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8e3812897d7996b59a52e62a5bd6b99f35ff4affb4b7b94f08322fafb1c52710", "generation_seconds_batch": 23.957144370069727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9293553233146667, "target_z": 0.7773437272966403, "ce": 5.629451274871826, "genuineness": 4.607763767242432, "identity": 0.6288529634475708, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/59c0414da5693081080d9fd8553695cc1a16c61954abf3c01d31cd57a2f92451.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "59ebd10468e51c0e679d8cb71450ddfb21926b270469af1d2da2240daaacdb61", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e343387bd054ea3b4d8ae370938c55f33ecc025d8a73207562d22ba943a0c18b", "generation_seconds_batch": 22.86704268702306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0858293771743774, "target_z": 1.0234375073236643, "ce": 5.637393951416016, "genuineness": 4.557555198669434, "identity": 0.1993216574192047, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/59ebd10468e51c0e679d8cb71450ddfb21926b270469af1d2da2240daaacdb61.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "59f488269b9aed2ee926dbf4ce5d49c5bea8564ef0c73cdc8f349cc00c30ac78", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "56765e5c42bd4ea4a5335627a629978abf40e2b8240db6d11fe194b67e69bca4", "generation_seconds_batch": 18.46703456202522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9948689937591553, "target_z": 2.4531249853526713, "ce": 6.157639026641846, "genuineness": 4.808597087860107, "identity": 0.8685399293899536, "hypothesis": "j'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/59f488269b9aed2ee926dbf4ce5d49c5bea8564ef0c73cdc8f349cc00c30ac78.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "5a1e121f5c4c80d15f7c3db0efaa3003635cf643f3b615c380e0f5c11ed26939", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4b57dcf622758b997cf3e2baf9b4d6699b0257b8b75c8cc0a0afe60bbf7f80ab", "generation_seconds_batch": 22.509251386974938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2348523139953613, "target_z": 1.2578125805603089, "ce": 5.879645347595215, "genuineness": 4.432034492492676, "identity": 0.5967941880226135, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5a1e121f5c4c80d15f7c3db0efaa3003635cf643f3b615c380e0f5c11ed26939.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "5a8310ac2645b2a0840dfae0419ded9d6f87474696036ce430c7b5da5651dc90", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9394931c31bbf949970f800368bede7b14eec7e78860b028f18b5a91d7a681c1", "generation_seconds_batch": 23.375367445056327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5791515111923218, "target_z": 0.22656244580488313, "ce": 5.895530700683594, "genuineness": 4.406930446624756, "identity": 0.4389432668685913, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5a8310ac2645b2a0840dfae0419ded9d6f87474696036ce430c7b5da5651dc90.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "5ada1e1a97c22ea96b8aefe91d50da308aa1ca20b6b57b33dc645aac6b3a3fc2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3f2eeb96ffc6734db8ba32a4d0868ccd184f18eb8d1d77a923efe9e37fc4c193", "generation_seconds_batch": 15.359590281965211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7763020992279053, "target_z": 2.1093750029294656, "ce": 5.236289024353027, "genuineness": 4.331617832183838, "identity": 0.3972569406032562, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5ada1e1a97c22ea96b8aefe91d50da308aa1ca20b6b57b33dc645aac6b3a3fc2.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "5aec3d55a738f6c3407de1ae1387835640287fdbcafa330addd9d04d4dd8c5e3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6621c821a9789383305a982eddf4855de4f1bc00127cf5288523134d7a0dc1c4", "generation_seconds_batch": 26.297258412931114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.364005446434021, "target_z": 1.4609375190415275, "ce": 6.324435234069824, "genuineness": 4.557555198669434, "identity": 0.2497866451740265, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5aec3d55a738f6c3407de1ae1387835640287fdbcafa330addd9d04d4dd8c5e3.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "5af34a4f94726fb856e0ac27ec235afb0d42723caf3e04450141e9296c23b983", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "02f3a67317be016519a1f5b2ee2fb799597889b81136a87546e14b5ca29b4c2e", "generation_seconds_batch": 26.27866603806615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1206014156341553, "target_z": 1.0781250556598498, "ce": 6.475345611572266, "genuineness": 4.607763767242432, "identity": 0.5928453207015991, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5af34a4f94726fb856e0ac27ec235afb0d42723caf3e04450141e9296c23b983.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "5b1e97f6b00cedb5295236fa01e4f915dc259017617c5d28064dffc34637a083", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ca43591e3a6d4a791f5953dea49ecbb3ac1a20494f1023bb538b32fda495cc6", "generation_seconds_batch": 17.693163283052854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5577352046966553, "target_z": 1.7656250205062605, "ce": 5.919358730316162, "genuineness": 4.325342178344727, "identity": 0.658034086227417, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5b1e97f6b00cedb5295236fa01e4f915dc259017617c5d28064dffc34637a083.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "5b21f77fd21f1a7cebebfc255a541413654ea4653aeb6d9e75cc09974285a85a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2fe232bb4e39a86ca0aed8313190641299f05852cf5b2e252f7b21059a568e08", "generation_seconds_batch": 23.584301147959195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0187690258026123, "target_z": 0.9179686774957221, "ce": 6.173524379730225, "genuineness": 4.394378662109375, "identity": 0.724499523639679, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5b21f77fd21f1a7cebebfc255a541413654ea4653aeb6d9e75cc09974285a85a.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": "5b803d0a11f46624c6f119086aef37e228f205342b65193f3f44d68e4704d632", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "baa833bd7da0b1e67d42a8cd8537e6cf4f3f98ad56fe3a9f76583efacaa474e5", "generation_seconds_batch": 19.478918959968723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8871321678161621, "target_z": 0.7109374721700751, "ce": 5.5539960861206055, "genuineness": 4.507347106933594, "identity": 0.6569592356681824, "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_Longing/5b803d0a11f46624c6f119086aef37e228f205342b65193f3f44d68e4704d632.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "5b86dc69af941a3075c0f840646464ecef70f40b0f7f136ab23c0f21ca613e3f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d10232b6153f2ee610f24afaf87ae03c3fa043b4ae3aa5336444f64c6b3f36cc", "generation_seconds_batch": 24.585544439032674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4037449359893799, "target_z": 1.5234376010665693, "ce": 6.268836498260498, "genuineness": 4.645420074462891, "identity": 0.43603309988975525, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5b86dc69af941a3075c0f840646464ecef70f40b0f7f136ab23c0f21ca613e3f.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "5bbdee304a09f00367b3c9d4a2c876d61f89fbd63dd7c86cdce97b5cd009d12e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b101657f30bab68b0dfda5690b7955c7119b242f857631edbb7e583f1275c4a5", "generation_seconds_batch": 16.43763546308037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.392263412475586, "target_z": 3.0781250556598496, "ce": 5.847874641418457, "genuineness": 4.7081804275512695, "identity": 0.7786603569984436, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5bbdee304a09f00367b3c9d4a2c876d61f89fbd63dd7c86cdce97b5cd009d12e.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "5bd37f3950f43a076cc53396fe966475aecda4465750d9724b2c0a7c990a8efd", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6e79c8bf502b5fd6855716f1353c018b75fd5700beff514868d529c66ea5346b", "generation_seconds_batch": 24.395739836036228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7219651341438293, "target_z": 0.451171851930457, "ce": 5.649308204650879, "genuineness": 4.570107460021973, "identity": 0.21797271072864532, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5bd37f3950f43a076cc53396fe966475aecda4465750d9724b2c0a7c990a8efd.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "5c0716bb19bbb3f7f60f03c1f9c74162ae8a71b398104f609312897c7f4b11a9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "25bccb1216a0cc43aefe867d4e133a56ac207543fbef9d6743db432de69742ca", "generation_seconds_batch": 24.060074107022956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5518306493759155, "target_z": 0.18359369800198247, "ce": 6.23706579208374, "genuineness": 4.231201171875, "identity": 0.30177849531173706, "hypothesis": "The door is still open. Put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5c0716bb19bbb3f7f60f03c1f9c74162ae8a71b398104f609312897c7f4b11a9.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "5c3c688c72ef4278d38b26dadc990b1bddc43e7a05fc00cb830282308a314699", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3478fb51c72d5227f00218e11ee263755e4a886ee71daf971199fd0f10866525", "generation_seconds_batch": 16.879675847943872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2835894823074341, "target_z": -0.23828124633816777, "ce": 6.260893821716309, "genuineness": 4.362998008728027, "identity": 0.2474643737077713, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5c3c688c72ef4278d38b26dadc990b1bddc43e7a05fc00cb830282308a314699.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "5c658f86f65dd755bdb0b7668b08db29956e1306937d6f6c9ccc2b1c3a507ee2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e7e251edc47fa36537684ad0fbff49743fdb385f37b9faa246b4cff7b3847049", "generation_seconds_batch": 22.500964435981587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6785001754760742, "target_z": 0.3828125571245826, "ce": 6.157639026641846, "genuineness": 4.381826400756836, "identity": 0.8291370868682861, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5c658f86f65dd755bdb0b7668b08db29956e1306937d6f6c9ccc2b1c3a507ee2.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": "5d20e2455f308301bfdb51ab01afa2bba2ef234e8b216f81606774c4061b633e", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d005c0fccfaa170084c1000af50cf2319b444b761db736d64cc0caa3dcb0d469", "generation_seconds_batch": 19.022052870946936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0346083641052246, "target_z": 2.515624879891903, "ce": 6.0146708488464355, "genuineness": 4.7332844734191895, "identity": 0.7537527084350586, "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_Longing/5d20e2455f308301bfdb51ab01afa2bba2ef234e8b216f81606774c4061b633e.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "5d896163624c1db0b68e31179e5fc16a4fed84bd35135a973066090659674b2e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "aa3493fb0e2e337fce0b89180c8447e5448664ed8e2f69c541b21af7f16032ad", "generation_seconds_batch": 27.964692324982025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2298848628997803, "target_z": 1.2500000468714525, "ce": 5.895530700683594, "genuineness": 3.9676074981689453, "identity": 0.29886847734451294, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás libre.", "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_Longing/5d896163624c1db0b68e31179e5fc16a4fed84bd35135a973066090659674b2e.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "5dd29b918319245887b1d5e565aee9572c7de84af6291d39ed206455c29faf35", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3adeaae5cde0e8114df5ec66520056f593e0f322a2747df815f55bd6f388a38d", "generation_seconds_batch": 22.83371040597558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5875396728515625, "target_z": 1.8124998476677796, "ce": 6.24500846862793, "genuineness": 4.65797233581543, "identity": 0.32683372497558594, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5dd29b918319245887b1d5e565aee9572c7de84af6291d39ed206455c29faf35.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "5df06dba0bb8e193bc1d7c1c5b11fabfda6ab853ef887b9acd6b59afb2932489", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b45b5b72573ceeae07a1dcba22d2c4d766c377f67fbaf32a138e968bd9f95cfb", "generation_seconds_batch": 24.938349273987114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6573885679244995, "target_z": 0.34960938268984765, "ce": 6.427689552307129, "genuineness": 4.375550270080566, "identity": 0.3739042580127716, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5df06dba0bb8e193bc1d7c1c5b11fabfda6ab853ef887b9acd6b59afb2932489.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "f31ea33d92996d8e82207b4cc70208786034aa585912cb287843a00af65b6323", "generation_seconds_batch": 19.213704110006802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24757561087608337, "target_z": -0.29492188122511476, "ce": 6.141753673553467, "genuineness": 4.3504462242126465, "identity": 0.8930947780609131, "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_Longing/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "heldout-de-3", "language": "de", "sentences": [ "Jemand hat den kleinen blauen Stuhl umgestellt.", "Er stand hier... neben dem hohen Bücherregal.", "Wir stellen ihn nach dem Essen zurück." ], "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-3", "key": "5e28ca90af8015099d3bcc8380b18149d378eb543b1b171c0327c982c9c04eec", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "183cef7c336de9f3d73e6dbef63cec3037b9fa16d7c3c1592f1fefd0a83d6ccf", "generation_seconds_batch": 19.478918959968723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9889644980430603, "target_z": 0.871093756591298, "ce": 5.895530700683594, "genuineness": 4.7332844734191895, "identity": 0.6130130290985107, "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_Longing/5e28ca90af8015099d3bcc8380b18149d378eb543b1b171c0327c982c9c04eec.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "5e9c57ca32794b1da786ef77ddfefae8a7df6f9fd79dda0d8c264edb5fdd8f82", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "64834b891ee6d84eb2cc9c6521dde6b5356a1684f5f562bf4d39c05a17e99f37", "generation_seconds_batch": 24.031223485944793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7961719036102295, "target_z": 2.1406251376848915, "ce": 6.372091293334961, "genuineness": 4.532451152801514, "identity": 0.40604445338249207, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5e9c57ca32794b1da786ef77ddfefae8a7df6f9fd79dda0d8c264edb5fdd8f82.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "5eb9f61fb4fefd4cd0b79c77276a65723781bb7cd25c0c7446fb68f685cb0efa", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "20d7ee286bc626eb2c35daa53724c00472d26d4f92592c8893ef21bd620709af", "generation_seconds_batch": 24.35175823199097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1653082370758057, "target_z": 1.1484374838879383, "ce": 5.831989288330078, "genuineness": 4.65797233581543, "identity": 0.5418864488601685, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5eb9f61fb4fefd4cd0b79c77276a65723781bb7cd25c0c7446fb68f685cb0efa.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "5edae3fea31b6ee29b5cb5783fa6c95d909298325d2ff51f792d89b4fd771632", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c0fbc84676a62ec4b33d0fcc2e246b211bf7903beb861ffb31d219cc0e9bda0e", "generation_seconds_batch": 22.923228472005576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0858293771743774, "target_z": 1.0234375073236643, "ce": 6.046441555023193, "genuineness": 4.557555198669434, "identity": 0.7214313745498657, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5edae3fea31b6ee29b5cb5783fa6c95d909298325d2ff51f792d89b4fd771632.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "5f0b1077395951b1c59d76d833eeee8b21ad3ad8139518213d4687573bb6dad4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c621c94d7e0b6835bb68b6f50ce0d2b3e827503ad7415425a4c413e3cec7f2de", "generation_seconds_batch": 21.90754825703334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21280360221862793, "target_z": -0.34960938268984765, "ce": 5.990842819213867, "genuineness": 4.607763767242432, "identity": 0.4487876892089844, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5f0b1077395951b1c59d76d833eeee8b21ad3ad8139518213d4687573bb6dad4.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "5f9c9d1a21b57777b805639bfcdbedbc5d887f4421d295e8e6d57aa3c507aac1", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8041bf4f2c7abbd70079a89a96ef7863f37086a6bf97f9cbedf33bf6e032e77a", "generation_seconds_batch": 24.696026649908163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.423614501953125, "target_z": 1.5546873608503757, "ce": 5.95112943649292, "genuineness": 4.369274139404297, "identity": 0.33391088247299194, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5f9c9d1a21b57777b805639bfcdbedbc5d887f4421d295e8e6d57aa3c507aac1.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "5fc05e3904508dc984da02274ab2389350203582547ac0f750bcd5d14c9e0673", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c7bc7e5f1f811d59921694a3e7a96bd58263438d65b96f0bb68c81c612de21d1", "generation_seconds_batch": 22.132505715009756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3043962717056274, "target_z": 1.3671874897468699, "ce": 5.772419452667236, "genuineness": 4.720732688903809, "identity": 0.8054074048995972, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/5fc05e3904508dc984da02274ab2389350203582547ac0f750bcd5d14c9e0673.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "6062d8b88469550478ec44ab2da24aff63bf7b998064a19cb0283ebb3b5c65fa", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f8d8f532579b3908bf72de8bd9dd168a2cd122a48ea60cb8c47a1ddc9a6d1233", "generation_seconds_batch": 18.56309156899806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8672624826431274, "target_z": 0.6796875249004591, "ce": 6.109982967376709, "genuineness": 4.7081804275512695, "identity": 0.5147491693496704, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6062d8b88469550478ec44ab2da24aff63bf7b998064a19cb0283ebb3b5c65fa.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "61534e4fe32cb8bae54348082eebe3f41545f8cf9668943702d7dd0b9941e82d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c9bd84de185742b99fa7fd26917226bbf1f2e3acc7c3510de64e63cad284c54a", "generation_seconds_batch": 24.936994355986826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9451947212219238, "target_z": 2.3750000234357262, "ce": 6.23706579208374, "genuineness": 4.482243061065674, "identity": 0.3977149426937103, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/61534e4fe32cb8bae54348082eebe3f41545f8cf9668943702d7dd0b9941e82d.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "618d3cbf58da4086b076f3b1ab5355a7e4df43f036010c511f7a2fbb5b476088", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "963328933860ec8854064699a580375a797793182790dc3677a364bc5bb6584b", "generation_seconds_batch": 17.76751710800454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6884349584579468, "target_z": 0.3984374370164858, "ce": 5.804190158843994, "genuineness": 4.20609712600708, "identity": 0.5146865248680115, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/618d3cbf58da4086b076f3b1ab5355a7e4df43f036010c511f7a2fbb5b476088.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": "61a91e10f8b9d5b6e510bbae1f8325716680cfc915ed6345b8368c6807ff5448", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80e971e4be9386fd13b4987b261f744f2f52e5f6fc3ae2390bd738bd8e900e82", "generation_seconds_batch": 22.621514161932282, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7256907224655151, "target_z": 0.45703125219709934, "ce": 6.125868320465088, "genuineness": 4.595211505889893, "identity": 0.7706292867660522, "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_Longing/61a91e10f8b9d5b6e510bbae1f8325716680cfc915ed6345b8368c6807ff5448.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "61eba65f07d7a13397ab1c902b2f813bb5386e399d4f787250eb2c1f926577c6", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5f786fadd11d6c905a1efaea0cbea83afec5fe445f9090d7e3ead66987c936e8", "generation_seconds_batch": 18.639138302998617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5478003025054932, "target_z": 1.7499999531285475, "ce": 6.443574905395508, "genuineness": 4.65797233581543, "identity": 0.4737972915172577, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/61eba65f07d7a13397ab1c902b2f813bb5386e399d4f787250eb2c1f926577c6.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "6214043e39fa7c74736ea30c14e62e410b38e42b3a27ec7c883357159e05df1b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "989c99b15043a584ba871b1838b979a1be84602d6810f6c2af99d1dd3378db0b", "generation_seconds_batch": 21.59007122600451, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0113179683685303, "target_z": 0.9062500644482471, "ce": 6.086154937744141, "genuineness": 4.758388519287109, "identity": 0.7177757620811462, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6214043e39fa7c74736ea30c14e62e410b38e42b3a27ec7c883357159e05df1b.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "6261392e68912151bdc878546ec9b4fa291c55e842dfd1203c4d7a731361824c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1b7d3caf42d7c827dae87537baa50f8fa3b6d9c1c663a038fa2fb53769d909ca", "generation_seconds_batch": 18.183218426071107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.628825843334198, "target_z": 0.3046875014647329, "ce": 6.213237762451172, "genuineness": 4.607763767242432, "identity": 0.6026313304901123, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6261392e68912151bdc878546ec9b4fa291c55e842dfd1203c4d7a731361824c.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "62fbd3023668d26000768ce718c7c2ded11edec7687b7ddaf900aa7544f4b756", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5349dbf60933c5e7630a8818549022e2111753e7fcc396e389a7e270e8a0fb60", "generation_seconds_batch": 26.297258412931114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2646567821502686, "target_z": 1.304687407721828, "ce": 6.2767791748046875, "genuineness": 4.444586753845215, "identity": 0.57224041223526, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/62fbd3023668d26000768ce718c7c2ded11edec7687b7ddaf900aa7544f4b756.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "6380181e6c83db948332101fedd49021669c521008fb49ed29228f62e79c6ed0", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19e7761963997beb8543d2bee405e030eeb83a115d04143289720aba62b25463", "generation_seconds_batch": 21.946329755010083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0336713790893555, "target_z": 0.9414062785622913, "ce": 6.165581703186035, "genuineness": 4.482243061065674, "identity": 0.6348283290863037, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6380181e6c83db948332101fedd49021669c521008fb49ed29228f62e79c6ed0.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "63ae26419182794e61373a8d85ae5b32b4b8aaae9c8e7932fc20ff44c87a5cda", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6b722334acd6a45b97fd232741caffe648fe504543fb1d6bfe40c7954d9a28e4", "generation_seconds_batch": 22.828300950932316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3689727783203125, "target_z": 1.4687498652445743, "ce": 6.1020402908325195, "genuineness": 4.7834930419921875, "identity": 0.7373070120811462, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/63ae26419182794e61373a8d85ae5b32b4b8aaae9c8e7932fc20ff44c87a5cda.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "63f8fcaa6f38441c3c18e62ecdb379f07bce80f557edba568b1d32aab38a4e07", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2e6a2d960048b94d0fd318088d0a96555d54fcb0533a8ba3acdae033211dfd16", "generation_seconds_batch": 21.900604802998714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47483551502227783, "target_z": 0.0624999882821369, "ce": 6.205295085906982, "genuineness": 4.532451152801514, "identity": 0.6684253811836243, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/63f8fcaa6f38441c3c18e62ecdb379f07bce80f557edba568b1d32aab38a4e07.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "646e2d979528983aa052d021ab34ff55ce61160c10739e00a44a11e4320f2390", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8657361f1dbb9736ebd8d5f113b1d4c724d26057a06802a3fc4ae2102c0612b5", "generation_seconds_batch": 22.281035950989462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7530115842819214, "target_z": 0.5, "ce": 6.348263263702393, "genuineness": 4.632867813110352, "identity": 0.5625016093254089, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/646e2d979528983aa052d021ab34ff55ce61160c10739e00a44a11e4320f2390.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "6498386b060aab2022724fa7829f92b97f22ce0f951ffced1d89be81c9aaaf6f", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1e33c864d4f41b2472a4bcfe23327dcb84ae71795ac4553dd888f5907846cb65", "generation_seconds_batch": 19.581561313010752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2398197650909424, "target_z": 1.2656251142491652, "ce": 6.157639026641846, "genuineness": 4.7081804275512695, "identity": 0.7474873065948486, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6498386b060aab2022724fa7829f92b97f22ce0f951ffced1d89be81c9aaaf6f.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "64eb885165f65e90cbf6e6e1821ee93eedf9f740a3623f5d39f668b8d85db0f1", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "88227be9ba3ebc26e7d613fd6bd8efac16d7d3adc326739cc1eaadb42f0cf78d", "generation_seconds_batch": 24.059402165934443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.855781078338623, "target_z": 2.2343751669795493, "ce": 5.065521717071533, "genuineness": 4.268857479095459, "identity": 0.457910418510437, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/64eb885165f65e90cbf6e6e1821ee93eedf9f740a3623f5d39f668b8d85db0f1.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "6531c0c1762526eaa415362d1b1b5055b139a1d50f823301be7f9ef51cf41744", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cad543f3c6e95aed3583e419c42eaeeaecfb2495393ded4aab4c0b2da4ea037f", "generation_seconds_batch": 25.191833373974077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0411224365234375, "target_z": 0.9531248916097663, "ce": 6.0305562019348145, "genuineness": 4.645420074462891, "identity": 0.14160361886024475, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6531c0c1762526eaa415362d1b1b5055b139a1d50f823301be7f9ef51cf41744.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "655054c25bdd155f44ace24b8912229c76a5c29455ae4ee658bf6ca5c48f572c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2374119068da5253651f9500b4a589a1fd714776e54f32406db7376040a4ed84", "generation_seconds_batch": 24.35175823199097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.795234739780426, "target_z": 0.5664062551265651, "ce": 5.974957466125488, "genuineness": 4.293961524963379, "identity": 0.5698055028915405, "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_Longing/655054c25bdd155f44ace24b8912229c76a5c29455ae4ee658bf6ca5c48f572c.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "6559d028ff1fa1812c00713d80e023490120d5d7ff482e9a3079e8b5989c9c1e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "29e7ae50d3574f23125d550fd95494c46a8192117b1c75e4fbfbd5501d4ecd8f", "generation_seconds_batch": 22.154107308015227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1851780414581299, "target_z": 1.179687618643364, "ce": 5.871703147888184, "genuineness": 4.909013748168945, "identity": 0.6397445201873779, "hypothesis": "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_Longing/6559d028ff1fa1812c00713d80e023490120d5d7ff482e9a3079e8b5989c9c1e.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "6573c9636966c556f34d9c659f7a61c49d4b8eeacec33df420ced8628d7dbf66", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b18ee044a3475890afb27c70c0d51824b6a5767a6116a74e0bf921b90831b637", "generation_seconds_batch": 18.48456936806906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7763020992279053, "target_z": 2.1093750029294656, "ce": 5.80021858215332, "genuineness": 4.758388519287109, "identity": 0.8014363050460815, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6573c9636966c556f34d9c659f7a61c49d4b8eeacec33df420ced8628d7dbf66.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "6579626b3b2e2d5711cd40db4242fcf5ee7d18dc9f1488176bcf87d862e031d3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "aee6b559dc6fc025926661597b0a4e17ec77df696446f177def99e88662ad98f", "generation_seconds_batch": 25.191833373974077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8424253463745117, "target_z": 0.6406250439419866, "ce": 6.0305562019348145, "genuineness": 4.519899368286133, "identity": 0.6383000612258911, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6579626b3b2e2d5711cd40db4242fcf5ee7d18dc9f1488176bcf87d862e031d3.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "65827b5e893be30e7fdb2ce4f1ee8c3ad1525be2c7f27ca97c6d5d7a6015341a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f4b7902ff428175c38105c7820d6490ef82ced6bb603b97c05f4f16412a6bf26", "generation_seconds_batch": 20.230708951014094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5263726115226746, "target_z": 0.14355469720385539, "ce": 5.927301406860352, "genuineness": 3.8671910762786865, "identity": 0.4056009352207184, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/65827b5e893be30e7fdb2ce4f1ee8c3ad1525be2c7f27ca97c6d5d7a6015341a.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "658fd74caa6ab7af463f8900184ffdcfeb2d6dd67bd85bd9c205fee4f69de30c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "18eb0d9042241a11a825a8018cbaed359af22225ad1df83f498824a91082fe73", "generation_seconds_batch": 24.78802579001058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9939319491386414, "target_z": 0.8789062902801544, "ce": 5.831989288330078, "genuineness": 4.168440818786621, "identity": 0.5000773668289185, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/658fd74caa6ab7af463f8900184ffdcfeb2d6dd67bd85bd9c205fee4f69de30c.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "65ed478f900d7cce01b818ee77049a9a05398f0cb7f03559982f1da36edbf006", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e49198513cb1b876d93afe5bcc5c891bababa46a474266283478f29d23049f6", "generation_seconds_batch": 23.26519695809111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2233707904815674, "target_z": 2.8125000351535894, "ce": 5.871703147888184, "genuineness": 4.7332844734191895, "identity": 0.6807796359062195, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/65ed478f900d7cce01b818ee77049a9a05398f0cb7f03559982f1da36edbf006.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "66a37eb3ecafd910305e1d1af4601c996796caba042763945b91aa5b865a3198", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4c11e03c06d23aa651c2ca577da9087e3902152609b208f1e0096d703eff2908", "generation_seconds_batch": 22.042502900934778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.550588846206665, "target_z": 0.1816406583226732, "ce": 5.879645347595215, "genuineness": 4.6956281661987305, "identity": 0.6502593755722046, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/66a37eb3ecafd910305e1d1af4601c996796caba042763945b91aa5b865a3198.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "67049486f6f6a543d0ef581b31bf0bc7077dc3fcdfd25a1f15220a7743bcc735", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7d564de854245e8395e61463071421901cabe3a23988cc393d3e59685d90fefc", "generation_seconds_batch": 23.26519695809111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.974999189376831, "target_z": 2.4218748505972454, "ce": 5.879645347595215, "genuineness": 4.821148872375488, "identity": 0.8538509011268616, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/67049486f6f6a543d0ef581b31bf0bc7077dc3fcdfd25a1f15220a7743bcc735.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "67106ae5a97b2dbc2331c5a70e31551a581fe28106d7da84e1842157dbd9e3ff", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "091d4750273ae9ebee033b177bc18732892b05f39a3ba4b45aa50a2b0fc1d5c4", "generation_seconds_batch": 22.429101904970594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8200718760490417, "target_z": 0.6054687360850376, "ce": 6.125868320465088, "genuineness": 4.6956281661987305, "identity": 0.7038611173629761, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/67106ae5a97b2dbc2331c5a70e31551a581fe28106d7da84e1842157dbd9e3ff.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "674b95e457e4f91ccbd86db0b753989a2f88edabac1f29c2c361de41fffef4d9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b7a552d7485ea5f4cb8a352dffc4913734d36e33634c4ec95cde9ff6eee122ff", "generation_seconds_batch": 25.281837988994084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9849340915679932, "target_z": 2.437499917974958, "ce": 6.181467056274414, "genuineness": 4.6203155517578125, "identity": 0.4547041654586792, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/674b95e457e4f91ccbd86db0b753989a2f88edabac1f29c2c361de41fffef4d9.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "67ad55197c56ce6fd1e5c55e54f4b3641af14abb789275e5869f2308ea18be4e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4240f0b8c4a0ae7da91e393b5698d03055f0ed00dc46583f24df8c303ebee775", "generation_seconds_batch": 25.124030200997368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5027773380279541, "target_z": 0.10644534966759703, "ce": 6.157639026641846, "genuineness": 4.532451152801514, "identity": 0.540123701095581, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/67ad55197c56ce6fd1e5c55e54f4b3641af14abb789275e5869f2308ea18be4e.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "683eab8d0470710c043ecb16ab4ccc2fb7c5a0e728c74b2afae51e6ec4b7e5dd", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e8503627cd881234ed475d8cce29946524afea43da40fd9ca5007ef97b79bbd", "generation_seconds_batch": 18.681189083959907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3838751316070557, "target_z": 1.4921874663111436, "ce": 5.95112943649292, "genuineness": 4.607763767242432, "identity": 0.5551013946533203, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/683eab8d0470710c043ecb16ab4ccc2fb7c5a0e728c74b2afae51e6ec4b7e5dd.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "685985ef5f205ad4996c98518f035145f6b110cff0283034cee45603c082dbdc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fd8968c7e81bc704a4c70e795795df88a1f2f95a487b20b8816c26d0c66658ec", "generation_seconds_batch": 19.186337475082837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8300067186355591, "target_z": 0.6210937097198456, "ce": 6.197352409362793, "genuineness": 4.507347106933594, "identity": 0.5426964163780212, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/685985ef5f205ad4996c98518f035145f6b110cff0283034cee45603c082dbdc.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "68a2490d4da1f82041b07e8d26a34590e2ee4f66bcc330f6bec41751af396364", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d85b1b69c3af166184f868844287876416272d9bf249519e469b0fecad453f57", "generation_seconds_batch": 23.92037905799225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.537865400314331, "target_z": 1.7343748857508348, "ce": 5.720792293548584, "genuineness": 4.532451152801514, "identity": 0.5697349309921265, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/68a2490d4da1f82041b07e8d26a34590e2ee4f66bcc330f6bec41751af396364.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "68f6d9fbface3cb2651dff8fec6d9dd61597a1f932e0e7cc2baa31b0c03d2b21", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8e9359163c8335130ec977f5d4f9f17f933a0956bc5bd327c703e71f3d73e785", "generation_seconds_batch": 22.084381639026105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3838751316070557, "target_z": 1.4921874663111436, "ce": 6.022613525390625, "genuineness": 4.494794845581055, "identity": 0.8027585744857788, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/68f6d9fbface3cb2651dff8fec6d9dd61597a1f932e0e7cc2baa31b0c03d2b21.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "69c07dbc6e5d9d7c489754333e657b657cde02d3da56a2da72c1f99d84810969", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "208a6d2aa96908d145952005d6d2c7fd41c19d075bba7ef406a91834d38fd0b3", "generation_seconds_batch": 25.026489630923606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6983698606491089, "target_z": 0.41406250439419867, "ce": 5.649308204650879, "genuineness": 4.024092197418213, "identity": 0.4273284673690796, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/69c07dbc6e5d9d7c489754333e657b657cde02d3da56a2da72c1f99d84810969.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "69e3d4663295ad710d2bdfc63f3ba4782f4ff4ab4d2a79c4fbaf2492dbea7124", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "739c358fe076b39eba4fc00aea41bd8efb02d19424a26139fe6142e318bff196", "generation_seconds_batch": 22.71651874994859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6660815477371216, "target_z": 0.3632812229024416, "ce": 6.1894097328186035, "genuineness": 4.68307638168335, "identity": 0.6363823413848877, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/69e3d4663295ad710d2bdfc63f3ba4782f4ff4ab4d2a79c4fbaf2492dbea7124.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "112f09ea1613c717670d1d35b4c104d5e888758d35aeaa8a6a0f4a5890ac4dc1", "generation_seconds_batch": 16.42544724792242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05012029409408569, "target_z": -0.6054687360850376, "ce": 6.2767791748046875, "genuineness": 4.18099308013916, "identity": 0.3746124505996704, "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_Longing/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "6b1fe022980deace1d16851b377d5168b518ec3ee96251f1fe228b6472478ffe", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dc2580039e2cc46e6f9718cdae1bd9edf79502a1e9c18f04a26a97f9bf58f8c3", "generation_seconds_batch": 24.280470261001028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9740622043609619, "target_z": 0.8476562492676336, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.6933630108833313, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6b1fe022980deace1d16851b377d5168b518ec3ee96251f1fe228b6472478ffe.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "6b351c1c5d807945f7ef2a196094392a4ecd00efa1b72e9e1f72e20b2e0888c9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7bf44f114e715f493ab7d14a2bf91769b939096405cff2101d1365c04945245e", "generation_seconds_batch": 26.005900869960897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8855855464935303, "target_z": 2.2812499941410684, "ce": 6.205295085906982, "genuineness": 4.482243061065674, "identity": 0.43590056896209717, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6b351c1c5d807945f7ef2a196094392a4ecd00efa1b72e9e1f72e20b2e0888c9.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "6b454e1e90e6a5819c2840b3cbf0c58749d3d66cb53b8b7b969658f4606b9a9a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4c1c7ed1ac04005fe87839fd737aea58bbe61a400a238c2523bb93b4054ec1b1", "generation_seconds_batch": 25.29324460308999, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5776050090789795, "target_z": 1.7968751552616862, "ce": 6.23706579208374, "genuineness": 4.482243061065674, "identity": 0.3613176941871643, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6b454e1e90e6a5819c2840b3cbf0c58749d3d66cb53b8b7b969658f4606b9a9a.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "82d00f9f82a71fc0556042e42a9feadfa4c6e7eed498c17ba56ff67688c987a3", "generation_seconds_batch": 17.983043245971203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13456657528877258, "target_z": -0.47265627270335975, "ce": 6.213237762451172, "genuineness": 4.545003414154053, "identity": 0.7163043022155762, "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_Longing/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "6b99164b97ecc718698b578192f9068e9f4ad29bb1a4d1e0e091b48abaee52df", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "944898c6941262e135345b97123a868152bad1a12a1e67ad9eff9305ada9c843", "generation_seconds_batch": 24.059402165934443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8955204486846924, "target_z": 2.296875061518781, "ce": 5.831989288330078, "genuineness": 4.369274139404297, "identity": 0.5175760984420776, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6b99164b97ecc718698b578192f9068e9f4ad29bb1a4d1e0e091b48abaee52df.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "6c8071d8516d731f7a5cad11d32881ec7c96ab865afebfbc4cccf8d4de693166", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3c7ba2ddeb895b4f98b09bd853b5bf938915a0da1d4146690471b9950adc58b", "generation_seconds_batch": 24.72701564594172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.974999189376831, "target_z": 2.4218748505972454, "ce": 6.205295085906982, "genuineness": 4.632867813110352, "identity": 0.4149031341075897, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6c8071d8516d731f7a5cad11d32881ec7c96ab865afebfbc4cccf8d4de693166.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "6d1851454b3f1ee8d03d74ceea6aab499f2519aebeb2d7d388b70ab9e0439e15", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6cb44a97bf8c26359b259aad4478a8c08a4a049e9289c907e1422c7e838444ed", "generation_seconds_batch": 23.43637649808079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9020344614982605, "target_z": 0.7343749794937395, "ce": 5.919358730316162, "genuineness": 4.7834930419921875, "identity": 0.6206629276275635, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6d1851454b3f1ee8d03d74ceea6aab499f2519aebeb2d7d388b70ab9e0439e15.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": "6d1f8c65edd29ca364b13e7d47eb9c36ffd4e4598d1949c78996ca17d668d256", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f55d0076a30ee13c7d0e33285f6f5634558f5e052330b3cd95acba74473d1fc2", "generation_seconds_batch": 24.232879484072328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9243879318237305, "target_z": 0.7695312873506887, "ce": 5.530168056488037, "genuineness": 4.65797233581543, "identity": 0.7508689165115356, "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_Longing/6d1f8c65edd29ca364b13e7d47eb9c36ffd4e4598d1949c78996ca17d668d256.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "6d694bcc9d64d0cd9d76d6617eddb67791b7ff1e0919421812da021184162762", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "71889ec731fdbff45c1f5e28c2fe93c4ed2cb405edb2df3edbb7d11c443c44a8", "generation_seconds_batch": 21.239217801950872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26744532585144043, "target_z": -0.2636718870840463, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.4985925555229187, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6d694bcc9d64d0cd9d76d6617eddb67791b7ff1e0919421812da021184162762.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "6e07357cc999cdd2047fbcc0c1092d4aba501415cd13b0f0f14bf7bde2edc949", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "866277cfed0a6b73b2151f2f337be7bae6c59560ee1eff6b88fd9ff80e8f4a6f", "generation_seconds_batch": 20.02037854702212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7492860555648804, "target_z": 0.4941406934762625, "ce": 6.348263263702393, "genuineness": 4.231201171875, "identity": 0.7049764394760132, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6e07357cc999cdd2047fbcc0c1092d4aba501415cd13b0f0f14bf7bde2edc949.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "6e248716dc5c13538b8780aea73e4e99863eb1f6c599306980045f6a4513e1c4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5ac86c2eaf0b789318f21fd93376ec1cd042b5a9be9cc63c85a1097e2d2f98dd", "generation_seconds_batch": 21.964383852900937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7067580223083496, "target_z": 1.9999999062570952, "ce": 5.6254801750183105, "genuineness": 4.557555198669434, "identity": 0.7203279733657837, "hypothesis": "La porte 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_Longing/6e248716dc5c13538b8780aea73e4e99863eb1f6c599306980045f6a4513e1c4.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "6e6a3581473ccef02771412ac35b392117d58d0534915f460fb1d4589f11bb4a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5562349828929a588b404a3428a860ec96b84624e530bee01ebb4a86c302b07", "generation_seconds_batch": 23.766848879982717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4683215618133545, "target_z": 1.6250001640500835, "ce": 5.9431867599487305, "genuineness": 4.7081804275512695, "identity": 0.5289629697799683, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6e6a3581473ccef02771412ac35b392117d58d0534915f460fb1d4589f11bb4a.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "6fe6e16a6228e97996ffe4d6748101f78485145cb0429cf5e09b42f41cf687c9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d392c1c23828286229a090fd99490165c5f25f4ebabfc58201038d13187dddb0", "generation_seconds_batch": 24.78802579001058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.205047607421875, "target_z": 1.2109373784271702, "ce": 5.935244083404541, "genuineness": 4.469690799713135, "identity": 0.6026690006256104, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/6fe6e16a6228e97996ffe4d6748101f78485145cb0429cf5e09b42f41cf687c9.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "7008f5475a0098c5f933ee89b86dacdb34c8a6e556404a7e0db4b3c19fafaeba", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7cdb89fec7069fe30a99bacc6495f5f3b8fac83921a0b408e666229d9ba071ac", "generation_seconds_batch": 23.507680029957555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5282353758811951, "target_z": 0.14648435046572414, "ce": 6.213237762451172, "genuineness": 4.457139015197754, "identity": 0.6332410573959351, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7008f5475a0098c5f933ee89b86dacdb34c8a6e556404a7e0db4b3c19fafaeba.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": "702b0dd89d72cbe001c136b1a1212c389d54ea9fb60693dc104f4ac7e3e020e7", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "43691439b08a04686afc1e851bdf1b422a583f8b00b69adddaa7d25d33fbd35e", "generation_seconds_batch": 23.880480770021677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0907968282699585, "target_z": 1.031250041012521, "ce": 5.95112943649292, "genuineness": 4.519899368286133, "identity": 0.6214244365692139, "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_Longing/702b0dd89d72cbe001c136b1a1212c389d54ea9fb60693dc104f4ac7e3e020e7.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "705c78be0ed4095f8ab63a314951dca8075ad3e70d0b6078ee91f4ec5587d60f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc3c46b06c775539241559a135cd398ca954882674b4b39c5fcc6260c9201ce7", "generation_seconds_batch": 22.556187741924077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5478003025054932, "target_z": 1.7499999531285475, "ce": 4.9900665283203125, "genuineness": 4.042920112609863, "identity": 0.4904205799102783, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/705c78be0ed4095f8ab63a314951dca8075ad3e70d0b6078ee91f4ec5587d60f.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "7121163bacdd2af897f721ede649faa47d2fd487a550dcbfb19190d3c850d4e5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c24136177f5b9499e96d3e2b57ff3b6bfbc3e60bed7e44c4f570bfb5fa4d8c10", "generation_seconds_batch": 18.367653392022476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.961643636226654, "target_z": 0.8281250087883973, "ce": 6.443574905395508, "genuineness": 4.362998008728027, "identity": 0.5252335071563721, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7121163bacdd2af897f721ede649faa47d2fd487a550dcbfb19190d3c850d4e5.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "7157f89127748c46e8cb126b3b85c2f12c3c207c6e031f083f2e590a42cacdde", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f4cfef3195aaba82c1ad234806c6560dc3c4a04d14d9cfc4018f38f8b6ca0031", "generation_seconds_batch": 25.099927076953463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3292334079742432, "target_z": 1.4062499707053422, "ce": 5.871703147888184, "genuineness": 4.356721878051758, "identity": 0.6537469625473022, "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_Longing/7157f89127748c46e8cb126b3b85c2f12c3c207c6e031f083f2e590a42cacdde.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "715ec5caedc37bf3a0222ed6e188c109f413c87e3592589f4493c5094271e631", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "60985e92e5679c6766b0ffbcdbbb5d69c3a1322d598855ed0d9643f7b6c9508c", "generation_seconds_batch": 28.541323916986585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5909491777420044, "target_z": 0.24511716644446474, "ce": 6.41180419921875, "genuineness": 4.256305694580078, "identity": 0.5935757160186768, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/715ec5caedc37bf3a0222ed6e188c109f413c87e3592589f4493c5094271e631.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": "71647e4d84f91e6058286c9c906d2e35d5db77a800679757caab3c315c14d918", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b12799ffdbe2ec8f1717f9287a5ac1d17b4a157d62a9486d68702a9191b01216", "generation_seconds_batch": 22.041905699996278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4878750145435333, "target_z": 0.08300779547248018, "ce": 5.585766792297363, "genuineness": 4.15588903427124, "identity": 0.15948393940925598, "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_Longing/71647e4d84f91e6058286c9c906d2e35d5db77a800679757caab3c315c14d918.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "7209f7dcd4dec60c929fd892ce7c4bd68701bc8ecc08da69b83ac94645116e81", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0654742b38cafe331775841ef9dd49311c67dce57a97d18c16b2fea728a70d31", "generation_seconds_batch": 28.112087878980674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7663671970367432, "target_z": 2.093749935551753, "ce": 5.673136234283447, "genuineness": 4.846253395080566, "identity": 0.7581263780593872, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Tais-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_Longing/7209f7dcd4dec60c929fd892ce7c4bd68701bc8ecc08da69b83ac94645116e81.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "725d6e100a777e4a429ba22f4308fcf886d8e3ae775ef23f5da1d9f1078381b2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b92c27dff337d94c80eb081b2c31bfbc14481bc74a769d7f855e92350f234940", "generation_seconds_batch": 18.46703456202522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8259763717651367, "target_z": 2.1874999648464106, "ce": 6.09409761428833, "genuineness": 4.6956281661987305, "identity": 0.7360436916351318, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/725d6e100a777e4a429ba22f4308fcf886d8e3ae775ef23f5da1d9f1078381b2.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": "729c06d6eb87599fd7795a0e72ff130481b4268332648fb1cd88d7bb76f335de", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "98ed84c4b6572aeee5561181852d2729b27fa75df1e42fa902956fcc40f1e16c", "generation_seconds_batch": 22.621514161932282, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6611141562461853, "target_z": 0.35546878295649, "ce": 6.022613525390625, "genuineness": 4.632867813110352, "identity": 0.5697911977767944, "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_Longing/729c06d6eb87599fd7795a0e72ff130481b4268332648fb1cd88d7bb76f335de.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "72db5d20cba16d5b06be0cb272cb793437c6812b414e85f70c7f96b31efebb31", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "444ec0544b537f8c3b6fcad4e157f934c154f1600f7ff75e174f8fec04956bc0", "generation_seconds_batch": 18.239294886006974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6024420261383057, "target_z": 1.835937448734349, "ce": 6.308549880981445, "genuineness": 4.507347106933594, "identity": 0.5201281905174255, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/72db5d20cba16d5b06be0cb272cb793437c6812b414e85f70c7f96b31efebb31.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "72ff00f9d7913adca645ac70d6a72be57db1403249615f7f3d75fb519928cf53", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "155de459c06d1a42255978ce056d1bf7226f50c84cf771ac775870580505a44f", "generation_seconds_batch": 27.707076077000238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3888425827026367, "target_z": 1.5, "ce": 5.5817952156066895, "genuineness": 4.507347106933594, "identity": 0.608983039855957, "hypothesis": "He encontrado la cajita y estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/72ff00f9d7913adca645ac70d6a72be57db1403249615f7f3d75fb519928cf53.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "732078d14e0b11351ca18f90949ad9c6674c0efd45b8b3570dafa65d6021cf3e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "21af0ebfd9a6cdcd2cd54cb0a3ff660022c14d837b173428014c5635df2fc0c4", "generation_seconds_batch": 23.214471339946613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24509190022945404, "target_z": -0.2988281246338168, "ce": 5.732706069946289, "genuineness": 4.582659721374512, "identity": 0.6128997802734375, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/732078d14e0b11351ca18f90949ad9c6674c0efd45b8b3570dafa65d6021cf3e.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": "73d49dfd947e87532bba2de8d7640209ffc7da19b1e4440b778d82c6f94df29c", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a950a0a73f0e182625a88dd5b8392ccf33612e27eb5e834f0dcfb526b2f5efe0", "generation_seconds_batch": 24.65904502104968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0560247898101807, "target_z": 0.9765624926763355, "ce": 5.585766792297363, "genuineness": 4.444586753845215, "identity": 0.8859752416610718, "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_Longing/73d49dfd947e87532bba2de8d7640209ffc7da19b1e4440b778d82c6f94df29c.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "7442441680842748966ae99ff72a3d6ab6b1412e605f89380812da914675c9f9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f43450dc0055d3ed18703cf2b1fb506d3e598dd45e70a24300f1aec478f373f9", "generation_seconds_batch": 25.372761911014095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6251002550125122, "target_z": 0.29882810119809056, "ce": 6.252951145172119, "genuineness": 4.7081804275512695, "identity": 0.7253520488739014, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7442441680842748966ae99ff72a3d6ab6b1412e605f89380812da914675c9f9.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "745ac97faf105a741c2eb58f1e1f936adb3b6203bd8cc26d74415ce257adc445", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3028712ce8a5c53a8d45639ce9f4efadd2756c960037a982ee0d30f2292b352b", "generation_seconds_batch": 25.30974334909115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.647148847579956, "target_z": 1.9062498769624374, "ce": 6.41180419921875, "genuineness": 4.645420074462891, "identity": 0.36014223098754883, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/745ac97faf105a741c2eb58f1e1f936adb3b6203bd8cc26d74415ce257adc445.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "7464c78651dd4631bc052e008758ba91ac297aefe507c3931e6d1148371e256e", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6971680e3d27f623af415f97d16ab83ca69fbb4e27ba19a3857d68fc24b83df2", "generation_seconds_batch": 18.691605882020667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1206014156341553, "target_z": 1.0781250556598498, "ce": 6.205295085906982, "genuineness": 4.545003414154053, "identity": 0.750360369682312, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7464c78651dd4631bc052e008758ba91ac297aefe507c3931e6d1148371e256e.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "7485ac78621313eedaced527112e06b045c2497da68f136d1027f697e4f5ddd6", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d9223b4c1de46481e58426c071d2ad1623e762f22e7a31ef030390152471a2c7", "generation_seconds_batch": 18.639138302998617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7166929244995117, "target_z": 2.015624973634808, "ce": 6.340320587158203, "genuineness": 4.494794845581055, "identity": 0.41749346256256104, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7485ac78621313eedaced527112e06b045c2497da68f136d1027f697e4f5ddd6.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "74f2c42791c36d9741cc09b48fe39ac5cc09bc499ec389966a4e92781084666a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0cccc593d496e3c5777f08130ee4db8d233283b0f79585edda75f7e243db84ae", "generation_seconds_batch": 24.8962869719835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3491032123565674, "target_z": 1.437500105460768, "ce": 5.95112943649292, "genuineness": 4.808597087860107, "identity": 0.7285977602005005, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/74f2c42791c36d9741cc09b48fe39ac5cc09bc499ec389966a4e92781084666a.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "7529e967bb7a78ddfa08aae5cd7c8d169a008e9954f5952426f51957dd8154df", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "db54697c80090cd8c2323468386290d3c3c66227d0c146e311b406443a0cbd3a", "generation_seconds_batch": 24.6354158410104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2798638939857483, "target_z": -0.2441406466048101, "ce": 6.006728172302246, "genuineness": 4.20609712600708, "identity": 0.650439977645874, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7529e967bb7a78ddfa08aae5cd7c8d169a008e9954f5952426f51957dd8154df.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "75e3e9a0d02fc3a74bab1728247eb6066eaeca7e4810ae6c69aee37ad0197507", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "01fe0d4384f1d28c98de6aa846457e5a61738954ad51b4dccce3241355458884", "generation_seconds_batch": 23.991243668016978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1802105903625488, "target_z": 1.1718750849545074, "ce": 5.839932441711426, "genuineness": 4.231201171875, "identity": 0.5076971650123596, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/75e3e9a0d02fc3a74bab1728247eb6066eaeca7e4810ae6c69aee37ad0197507.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "7629f3973600fafe53eb6961223769a7b3c1ab8efaa91252ca7d2c86b23b843b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd2bced6e6725a8850bee1dcd0a43c396f3ca9798bac741d274d2f738c1eaf97", "generation_seconds_batch": 24.92062608303968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3093637228012085, "target_z": 1.3750000234357262, "ce": 5.792276382446289, "genuineness": 4.419482707977295, "identity": 0.5699679851531982, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7629f3973600fafe53eb6961223769a7b3c1ab8efaa91252ca7d2c86b23b843b.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "770b073ce8aef5006d94949dcb2a6fc4ed0f7717fe2b674fbb8d222e8c0ddad9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2b898e38789413fb4d7bdaa8d392ecb6e44fd32aac642a7c1473575dbebdad33", "generation_seconds_batch": 25.281837988994084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.965064525604248, "target_z": 2.4062501581911517, "ce": 6.149696350097656, "genuineness": 4.331617832183838, "identity": 0.39559969305992126, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/770b073ce8aef5006d94949dcb2a6fc4ed0f7717fe2b674fbb8d222e8c0ddad9.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "385d0f0a594189e51c3ac8c8eb532a0f74c74df70c4edc5da3f25373a1e782fc", "generation_seconds_batch": 18.3529529790394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24136632680892944, "target_z": -0.3046875014647329, "ce": 6.308549880981445, "genuineness": 4.6705241203308105, "identity": 0.7931040525436401, "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_Longing/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "77b0a8a068c39f8095db6fc08666520eb0548636a872c4531c73ff9e8c384669", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ffdc4ee8ba849fa1a54f4118dc59c3af44502f3d8b6d514e7f5d6c05bad1354a", "generation_seconds_batch": 24.520259308977984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4136797189712524, "target_z": 1.5390624809584725, "ce": 5.9431867599487305, "genuineness": 4.457139015197754, "identity": 0.5411320328712463, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/77b0a8a068c39f8095db6fc08666520eb0548636a872c4531c73ff9e8c384669.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": "786f70e484095fe55b9c9b0ab0bd939a3d2e8ac303ce090cb6038e071a0a50ad", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9caa8286794df24707e0f0313237ed16ecbd5b1d9cc464cb95971ce0c6183efe", "generation_seconds_batch": 24.665397631004453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0048038959503174, "target_z": 2.468750052730384, "ce": 6.1020402908325195, "genuineness": 4.024092197418213, "identity": 0.6721193790435791, "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_Longing/786f70e484095fe55b9c9b0ab0bd939a3d2e8ac303ce090cb6038e071a0a50ad.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "7872387715b2eed39f6a058d8d99ea297b2d97c5845efb417adedbcfc7a45d39", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4f5216fbf78e05d9d0f27c751d703a723e572885cb866eb272ad014d0a38b202", "generation_seconds_batch": 23.98390544799622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0262202024459839, "target_z": 0.9296874780290066, "ce": 6.125868320465088, "genuineness": 4.557555198669434, "identity": 0.7881801128387451, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7872387715b2eed39f6a058d8d99ea297b2d97c5845efb417adedbcfc7a45d39.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "34b698dba552fc3db53368fbd6eb7a83e1320c6c5f50b502fde79fc9f48e4106", "generation_seconds_batch": 19.28716493700631, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05508771538734436, "target_z": -0.5976562492676336, "ce": 6.2767791748046875, "genuineness": 4.319066047668457, "identity": 0.644961416721344, "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_Longing/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "7a18a098f3d270128be2cabe9885fe2647ddba18ae6ff041e6aab4220e82bf2c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "805159829705d954c129dca51203208ec7d8d91036d04a3f01847511c7666f3e", "generation_seconds_batch": 24.689744382048957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9715784788131714, "target_z": 0.8437499824232053, "ce": 5.736677646636963, "genuineness": 4.293961524963379, "identity": 0.3977016806602478, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7a18a098f3d270128be2cabe9885fe2647ddba18ae6ff041e6aab4220e82bf2c.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "7a1cd496400b29e6c30298c04a3c935f6e41b487e380fe9a760df18510773810", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ffa016bb9b79b245a31fa2c941f57b0cc51fa6c486e475ae4745f190cf5580b2", "generation_seconds_batch": 25.183324287994765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5592818260192871, "target_z": 0.1953124985352671, "ce": 6.181467056274414, "genuineness": 4.507347106933594, "identity": 0.244533509016037, "hypothesis": "The door s is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7a1cd496400b29e6c30298c04a3c935f6e41b487e380fe9a760df18510773810.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": "7ab39cb10c321ba3323798975b4cb84a59f3d816597f46a27d85f3d511ba4429", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "372c58c17abcd674cf08376fc8878d5a3560ef0c15de129529e2bf59b20dee30", "generation_seconds_batch": 25.55105175601784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5679748058319092, "target_z": 0.20898433874786101, "ce": 5.903473377227783, "genuineness": 4.281409740447998, "identity": 0.56528639793396, "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_Longing/7ab39cb10c321ba3323798975b4cb84a59f3d816597f46a27d85f3d511ba4429.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": "7abc7f331001747a92ed88299f19ee42049c52bf4deae14b74a3b84a059f8cb8", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "006d6f8c4f4f12a5d2750c92eefd422b4a643f47201d98948a8737c2546c058a", "generation_seconds_batch": 24.119873189018108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24509190022945404, "target_z": -0.2988281246338168, "ce": 5.871703147888184, "genuineness": 4.193545341491699, "identity": 0.0530848391354084, "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": 0.120000000000001, "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_Longing/7abc7f331001747a92ed88299f19ee42049c52bf4deae14b74a3b84a059f8cb8.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "7ac04b4390b1af9a97653c5ec7e590bae6f8bb3b1c07efb156900012962c26aa", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2c49643b6c40a351d81a4a8758c1311c1bdc928c174f472965467cf7f59eed17", "generation_seconds_batch": 18.46386583405547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3491032123565674, "target_z": 1.437500105460768, "ce": 5.728734970092773, "genuineness": 4.494794845581055, "identity": 0.40363815426826477, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7ac04b4390b1af9a97653c5ec7e590bae6f8bb3b1c07efb156900012962c26aa.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "7ad18dd551611bde006fecbad20c47a61e7aae9a5116049febf8929dc37cb924", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "81ed9f353fd7e234a83f86f8c44f2cfaffcf7fbacd367647b2a8a583e2cc0752", "generation_seconds_batch": 16.43763546308037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6074094772338867, "target_z": 1.8437499824232053, "ce": 5.49045467376709, "genuineness": 4.507347106933594, "identity": 0.7769609689712524, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7ad18dd551611bde006fecbad20c47a61e7aae9a5116049febf8929dc37cb924.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "7b008d527941fec5fa7d7b55114c1611f86279bc5addf963f125d19f26c14ff5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "aaa0cc3602fbca8beaec3f8a8c87b6fa54036debcf6198a73cf89a253c406bef", "generation_seconds_batch": 24.503497874946333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.961643636226654, "target_z": 0.8281250087883973, "ce": 5.696964263916016, "genuineness": 4.024092197418213, "identity": 0.4398594796657562, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7b008d527941fec5fa7d7b55114c1611f86279bc5addf963f125d19f26c14ff5.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "7b40407f96730723c539a2d089056dfd6d644be7f44a4109ea3ae22813120ca0", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "29d1369040785899775edebf2483ca9d425a27ae6ada106b8893190b970cfc28", "generation_seconds_batch": 19.09108184208162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31711962819099426, "target_z": -0.185546878295649, "ce": 6.038498878479004, "genuineness": 4.557555198669434, "identity": 0.5662415027618408, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7b40407f96730723c539a2d089056dfd6d644be7f44a4109ea3ae22813120ca0.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "7b5d85a0236748a404072e7c0b7ea686556772d3ff2909a35cac35c30cc71f06", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8691df055d73ad44986164113c6114ae4d941555ce31eea39c546dd68d49003f", "generation_seconds_batch": 23.957144370069727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5990212559700012, "target_z": 0.257812486817404, "ce": 5.831989288330078, "genuineness": 4.507347106933594, "identity": 0.527340292930603, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7b5d85a0236748a404072e7c0b7ea686556772d3ff2909a35cac35c30cc71f06.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "7b85c23591cd49cb47dc1cd98fff343fa2fe7da50927eb0dea7e7ae56db0479b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ae2357571e553c4280607fbe99cb47f6adb77c27294b32692faa0bac1ebb9988", "generation_seconds_batch": 23.723022207035683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5170586705207825, "target_z": 0.128906243408702, "ce": 6.205295085906982, "genuineness": 4.444586753845215, "identity": 0.7338587045669556, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7b85c23591cd49cb47dc1cd98fff343fa2fe7da50927eb0dea7e7ae56db0479b.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "7bc1be4c27b6468ed668a30534168f1258a16b48e07193103cbe542bcc666af5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8c53c62cc8aea5769c7642880ed7a9c45b2f0b395d238fe107ace00912ba704e", "generation_seconds_batch": 25.146220876951702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8855855464935303, "target_z": 2.2812499941410684, "ce": 6.173524379730225, "genuineness": 4.494794845581055, "identity": 0.33899062871932983, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7bc1be4c27b6468ed668a30534168f1258a16b48e07193103cbe542bcc666af5.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "7c285936f7f64c73c2a191d36b5caa8fbd360b157a41e009e04fb2b28ac3244e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0acf77a0fd5d0f3a186227d83ef9f383a0dc99ae75c0aa9967b524a13993f8ef", "generation_seconds_batch": 18.500119201955386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2199499607086182, "target_z": 1.2343749794937395, "ce": 5.839932441711426, "genuineness": 4.256305694580078, "identity": 0.43821001052856445, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7c285936f7f64c73c2a191d36b5caa8fbd360b157a41e009e04fb2b28ac3244e.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "7ccc4a1444d9ea79d215dfdfe3ae274a397d697c30aec345dddf260f7afa2d80", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4c205ba932c516f4427b47dd398093cdea212055285221292690367a9b1d4cfc", "generation_seconds_batch": 26.25543559109792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.847392737865448, "target_z": 0.6484374838879382, "ce": 6.117925643920898, "genuineness": 4.319066047668457, "identity": 0.8475090861320496, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7ccc4a1444d9ea79d215dfdfe3ae274a397d697c30aec345dddf260f7afa2d80.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "7d1b879ffb4bbe934ad09e3c5a7932c546578760af0edde3c246e31c24da642d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4fa68c73960b28f18c3d7fcccdebf80439ec424b1a04a52797d411e5c1734477", "generation_seconds_batch": 32.740283814957365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4512402415275574, "target_z": 0.025390640745878545, "ce": 6.268836498260498, "genuineness": 4.6203155517578125, "identity": 0.677738606929779, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7d1b879ffb4bbe934ad09e3c5a7932c546578760af0edde3c246e31c24da642d.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "7d99e590a90b9c388480d1094df59c997dd7b28300a7f67d35ed6460046f3303", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "34e8d8edcf320ab17d30dffe142607cf54febddc65a70a4040f9cfbdc0db1b47", "generation_seconds_batch": 16.27116123691667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3093637228012085, "target_z": 1.3750000234357262, "ce": 5.9431867599487305, "genuineness": 4.7834930419921875, "identity": 0.5465105772018433, "hypothesis": "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_Longing/7d99e590a90b9c388480d1094df59c997dd7b28300a7f67d35ed6460046f3303.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "7dda3e615370599ceb8c7774696d4ff740e4364989c2a848f154e44b4d5ba8dd", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "08f89c3fd3ce93939294faf22f349bd3e1d178b703e096443436c7c3777e065b", "generation_seconds_batch": 24.4326223769458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6114398241043091, "target_z": 0.27734372729664025, "ce": 5.5738525390625, "genuineness": 4.1998209953308105, "identity": 0.32791876792907715, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuando estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7dda3e615370599ceb8c7774696d4ff740e4364989c2a848f154e44b4d5ba8dd.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "7de68471e50fb97f5bdc6b67e07e30d46eb7aa490f3c4137f1ca2179bfb86d7f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "07acea5325efa0269262df3f69ee9f4381085451d3d2ea0061b0c4a28ae3e48c", "generation_seconds_batch": 17.955596353043802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32643356919288635, "target_z": -0.1708984245004956, "ce": 5.990842819213867, "genuineness": 4.507347106933594, "identity": 0.5046176314353943, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7de68471e50fb97f5bdc6b67e07e30d46eb7aa490f3c4137f1ca2179bfb86d7f.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "7e75f6e7e3d003176c6fa634ba4d80cc21785af26baa181dc9627a88468d9621", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3af5090b59282dd2061a7557db257919283178022d723d00f4687118799012ae", "generation_seconds_batch": 25.193367805099115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.249754548072815, "target_z": 1.2812499941410684, "ce": 5.478540420532227, "genuineness": 4.582659721374512, "identity": 0.6480469703674316, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7e75f6e7e3d003176c6fa634ba4d80cc21785af26baa181dc9627a88468d9621.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "7ea6f4905401b0d8a315233692dd908cc78f4a6ea08a54426f8694d1a3217769", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3742f096085a4f6a4341b81a03988088c3ad4f7d0a24ccbc4ad458b676764c61", "generation_seconds_batch": 21.528980186907575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0560247898101807, "target_z": 0.9765624926763355, "ce": 5.911416053771973, "genuineness": 4.720732688903809, "identity": 0.8588534593582153, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7ea6f4905401b0d8a315233692dd908cc78f4a6ea08a54426f8694d1a3217769.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "7eab73c9a17e801baa669a7fff556be448cba44d87a18dd0ac82a59a2b71ab99", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ffd329425210a82c0d6fffd6f04632673be88c3ec304ee3da3dee1760e2d798c", "generation_seconds_batch": 18.406287388992496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1653082370758057, "target_z": 1.1484374838879383, "ce": 6.141753673553467, "genuineness": 4.369274139404297, "identity": 0.7155436277389526, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7eab73c9a17e801baa669a7fff556be448cba44d87a18dd0ac82a59a2b71ab99.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "942ec1b57a0e9b78c9ca7cb348aef3b65e6d40da68fb0ea2868de58df997c796", "generation_seconds_batch": 19.043600006960332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4065333604812622, "target_z": -0.04492188122511477, "ce": 6.499174118041992, "genuineness": 4.406930446624756, "identity": 0.35163620114326477, "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_Longing/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "7fb76f95345812d4a8da88273990bd863185cbe75c76412631817e13b7a0c28b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "64e559a51e7ae9f7ff476aeffda8b5e63d3a8e78d6627d95c8426615052463ab", "generation_seconds_batch": 22.77882079198025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9666110873222351, "target_z": 0.8359375424772537, "ce": 5.967014789581299, "genuineness": 4.262581825256348, "identity": 0.4076962172985077, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/7fb76f95345812d4a8da88273990bd863185cbe75c76412631817e13b7a0c28b.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": "7fdd0bc33477bd45458f45bafc448da93f7dd6574459b176c4f0d585b959d1aa", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7e626225751566674aa430b832ac206d5ba7d2399d1362fef31ee359dd4585b", "generation_seconds_batch": 24.14434112107847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1951128244400024, "target_z": 1.1953124985352672, "ce": 5.71682071685791, "genuineness": 4.344170093536377, "identity": 0.3830334544181824, "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_Longing/7fdd0bc33477bd45458f45bafc448da93f7dd6574459b176c4f0d585b959d1aa.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "8084f827c45a3a199b0a2d5a1b0263f42a838e0347a089403759ce612ce7c011", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3117d4988230ade735f00a92135ed5718ae89c3fbca51a17b634a0cc1c463c48", "generation_seconds_batch": 24.52983590599615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7166929244995117, "target_z": 2.015624973634808, "ce": 6.117925643920898, "genuineness": 4.632867813110352, "identity": 0.4949930012226105, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8084f827c45a3a199b0a2d5a1b0263f42a838e0347a089403759ce612ce7c011.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "80a229932046496f1d3880ce7d244daca1d6e6089d55c757b8c33f7ea04c26a7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dee3685edbea2ff8db5caea66a5e8c2ad919564ba7ac596154be4456458b4c46", "generation_seconds_batch": 23.497443866916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1206014156341553, "target_z": 1.0781250556598498, "ce": 5.5659098625183105, "genuineness": 4.331617832183838, "identity": 0.40800005197525024, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/80a229932046496f1d3880ce7d244daca1d6e6089d55c757b8c33f7ea04c26a7.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "ec7cd488dd464f6d9848c6b2b483dd26238585e460bf528738d72a0c7cb4fbd6", "generation_seconds_batch": 20.83617404801771, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36989855766296387, "target_z": -0.10253908282316881, "ce": 6.300607204437256, "genuineness": 4.6203155517578125, "identity": 0.7501988410949707, "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_Longing/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "810dc73ad2b86a5438b8164628d2ca7b1da42a4d6b3869b7686a4b0ce4cad914", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1dc50e3b5808be6cac4e0cfb659d527939757e445b04b1ab7575e9a012dbf555", "generation_seconds_batch": 21.754530976060778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0758945941925049, "target_z": 1.0078126274317614, "ce": 5.736677646636963, "genuineness": 4.111956596374512, "identity": 0.3689887523651123, "hypothesis": "The 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_Longing/810dc73ad2b86a5438b8164628d2ca7b1da42a4d6b3869b7686a4b0ce4cad914.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "813f24c81854b7c5287aa88a4064b4bf0f1d51418f9a125b6f4ec0ec21be8b5f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c86882e03e1686160404819e2dc05204c90eaf1653876082387bfc5a2b5337f", "generation_seconds_batch": 24.280470261001028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.036155104637146, "target_z": 0.9453125454067195, "ce": 6.125868320465088, "genuineness": 4.3127899169921875, "identity": 0.679048478603363, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/813f24c81854b7c5287aa88a4064b4bf0f1d51418f9a125b6f4ec0ec21be8b5f.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "81545deacbe99451d3a18c9001bd4783da2cd5c0bb123318b3c99da9b3ff9a49", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4194275a075e9996fa198041a2cca552fc397d538ed63e4c591aed8833afb439", "generation_seconds_batch": 22.828300950932316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5974745750427246, "target_z": 1.8281249150454926, "ce": 6.054384231567383, "genuineness": 4.632867813110352, "identity": 0.7477631568908691, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/81545deacbe99451d3a18c9001bd4783da2cd5c0bb123318b3c99da9b3ff9a49.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "825caf09625fd64dae55a9d587f920db933f1cd60a28222103f08f206ca74624", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1b4b0435460a8d62c4aaa2a9a7eb6b52f77fc183e92b6324f73a4a76f483a501", "generation_seconds_batch": 24.90495303401258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4706442654132843, "target_z": 0.05590822157147981, "ce": 5.974957466125488, "genuineness": 4.632867813110352, "identity": 0.5257980823516846, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/825caf09625fd64dae55a9d587f920db933f1cd60a28222103f08f206ca74624.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "8303c7b3af5f2ef46ab74d6b0972bd9a4cf42a655651ba598c6b794e6f69c51a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fde15d308bcb24668845c90898f0c01cd2aad51c882d3807934d8d17baaeaafc", "generation_seconds_batch": 21.795656185015105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5527677536010742, "target_z": 1.757812486817404, "ce": 6.260893821716309, "genuineness": 4.293961524963379, "identity": 0.48185694217681885, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8303c7b3af5f2ef46ab74d6b0972bd9a4cf42a655651ba598c6b794e6f69c51a.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "83091f94d20f7c96db9cc8771fe533b08571cbb89634d3d556bad144a45631ec", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "55ecb67c0e47b39a2b105914677b6a393e6466523f9ea579c6722f994c9a9443", "generation_seconds_batch": 25.45418433297891, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9948689937591553, "target_z": 2.4531249853526713, "ce": 6.221180438995361, "genuineness": 4.65797233581543, "identity": 0.7518705725669861, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/83091f94d20f7c96db9cc8771fe533b08571cbb89634d3d556bad144a45631ec.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": "832dc68a67d6915ffc2cd27d7365c08ef514f79453cea2c8e75d4833c1442627", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9158275ffb325077450bed8ae3dc3d10aa20adfd28f1bb8fb31db53ba601108d", "generation_seconds_batch": 19.03077532001771, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.319298505783081, "target_z": 1.3906249033276294, "ce": 5.9431867599487305, "genuineness": 4.532451152801514, "identity": 0.6832195520401001, "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_Longing/832dc68a67d6915ffc2cd27d7365c08ef514f79453cea2c8e75d4833c1442627.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "8353919cf01e963155a63d4768dcae8021b40a31586ebed6e2b9bf86803c1952", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0fe825b8e48eafb86accd12002007d777ba630d16e766aa9ce3abd9e5811a87e", "generation_seconds_batch": 22.87846678402275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.319298505783081, "target_z": 1.3906249033276294, "ce": 5.685050010681152, "genuineness": 4.457139015197754, "identity": 0.5859087109565735, "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_Longing/8353919cf01e963155a63d4768dcae8021b40a31586ebed6e2b9bf86803c1952.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "8362ebb4fa828da7bbf9df9d031e0c835d4879337fe069060c584400e5683498", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e4bb6202767ce82f03d075fbfae184343de8b0cb85bb39ec1599c7d32dcb8681", "generation_seconds_batch": 24.913294658996165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9343227744102478, "target_z": 0.7851562609854966, "ce": 5.871703147888184, "genuineness": 4.7081804275512695, "identity": 0.5035762190818787, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8362ebb4fa828da7bbf9df9d031e0c835d4879337fe069060c584400e5683498.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "839085bc3a5813cf96f735aae0b8542b98f1d6534af82d7c3da82259ed1fcf54", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3da1795c48168e2bf055aafc81b71825855dd48969d5d28569af82adfc319c17", "generation_seconds_batch": 26.400480692042038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2842104136943817, "target_z": -0.23730467962706073, "ce": 5.982900142669678, "genuineness": 4.582659721374512, "identity": 0.5923354625701904, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/839085bc3a5813cf96f735aae0b8542b98f1d6534af82d7c3da82259ed1fcf54.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "83d1aa4fba500554fd63df39a3061b2bd887ebb28832f6c2a1ef0d68af0701a2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cdedaacf4cec2453e6afeffb8440db01fbe86671c5871bcddfd62b34938eb697", "generation_seconds_batch": 22.368793018977158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0858293771743774, "target_z": 1.0234375073236643, "ce": 6.046441555023193, "genuineness": 4.6705241203308105, "identity": 0.6863852739334106, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/83d1aa4fba500554fd63df39a3061b2bd887ebb28832f6c2a1ef0d68af0701a2.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "84882b45bd61c43899c04011a8b785ea2d5429c38d99a0a74183cf8c09afbd3f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8fd7be2db72d0865afdfe029511f99b4ee0c0a780e8d6f5d37ae4186c29ce8d6", "generation_seconds_batch": 25.684325636946596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1851780414581299, "target_z": 1.179687618643364, "ce": 6.022613525390625, "genuineness": 4.632867813110352, "identity": 0.728305459022522, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/84882b45bd61c43899c04011a8b785ea2d5429c38d99a0a74183cf8c09afbd3f.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": "85574ab7aa6cdd97dbb92b85a976ad05ed174788779b0bb6b99e58ca1a7d2c42", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b2a8c2e240dd143e1ddf01c77a49e30648f716127f3fc2ca74aa35360b613b79", "generation_seconds_batch": 21.16335828602314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7778487205505371, "target_z": 0.5390624809584724, "ce": 5.927301406860352, "genuineness": 4.557555198669434, "identity": 0.5632863640785217, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/85574ab7aa6cdd97dbb92b85a976ad05ed174788779b0bb6b99e58ca1a7d2c42.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "856acf511433d0d455a2a26f3692f624222d2ad8c16c4451a89b859dc9d20956", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "37671a1c73218e0c3f99d7bcd15bfd18bef34aeed995b44e3658b0751d0752fe", "generation_seconds_batch": 23.961267848033458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39038920402526855, "target_z": -0.07031252197099332, "ce": 6.125868320465088, "genuineness": 4.645420074462891, "identity": 0.665887713432312, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/856acf511433d0d455a2a26f3692f624222d2ad8c16c4451a89b859dc9d20956.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": "858105e3eb15fd25bf9e2541a4881c8b7b85976192ed2dd5bc7a7329e12e10b3", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6da99d6845a4a8b2260cfd42c88d8837beedd5f02a78e131d884aa983108a660", "generation_seconds_batch": 19.30538588494528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.145438551902771, "target_z": 1.1171875366183222, "ce": 6.340320587158203, "genuineness": 4.632867813110352, "identity": 0.3893609941005707, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/858105e3eb15fd25bf9e2541a4881c8b7b85976192ed2dd5bc7a7329e12e10b3.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "85d01df54008cf342d954340a3d9ddcbf25043c85f91a264d849ac914399dcdb", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3cc69a76171cb637ea0c807218e40309d0d4f79cf8be7c292c67070494c41a2f", "generation_seconds_batch": 23.53832638298627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5627026557922363, "target_z": 1.7734375541951168, "ce": 6.086154937744141, "genuineness": 4.400654315948486, "identity": 0.7548243999481201, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/85d01df54008cf342d954340a3d9ddcbf25043c85f91a264d849ac914399dcdb.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "85d268ab3e8d58e7041e365bf059afca97a0089591fa159b42d07c802e912a7a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bfbba16507d277311fbfed08cf8e1816f5f6536f9396ad39a7396e6dc02f064e", "generation_seconds_batch": 22.894997863913886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43757981061935425, "target_z": 0.0039062668444282125, "ce": 6.252951145172119, "genuineness": 4.6203155517578125, "identity": 0.6318601369857788, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/85d268ab3e8d58e7041e365bf059afca97a0089591fa159b42d07c802e912a7a.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": "8611f0e4b2a18a827098689aaec4bb9d2aca5b15ec087bdaf40273ad4f42fdcb", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "26843e41f4fc7c2b5eca4bb04c439d5bb669fe00830c15cb30c03dc93003c97e", "generation_seconds_batch": 26.019273624988273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2745916843414307, "target_z": 1.320312475099541, "ce": 5.919358730316162, "genuineness": 4.268857479095459, "identity": 0.46153759956359863, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8611f0e4b2a18a827098689aaec4bb9d2aca5b15ec087bdaf40273ad4f42fdcb.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "8612ebf8340417bad2dea57bc9ca3efbc150707d2432e76f16ff11be2b1a4333", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d10acd208da9c82c75663559d612654028b0e19a08b784fcb524570bec081bf0", "generation_seconds_batch": 19.296857360983267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.14047110080719, "target_z": 1.1093750029294658, "ce": 5.935244083404541, "genuineness": 4.469690799713135, "identity": 0.5414553880691528, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8612ebf8340417bad2dea57bc9ca3efbc150707d2432e76f16ff11be2b1a4333.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "862a958157c9b35089d298de0a8f487465d44ff250abbe77fe565b892ff2bdfd", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "283e709d99f65d931263bebfcd654bd35bf68c5bf3805cc1c402fec84e97637f", "generation_seconds_batch": 24.26889091404155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7579790353775024, "target_z": 0.5078125336888564, "ce": 6.268836498260498, "genuineness": 4.080576419830322, "identity": 0.15022613108158112, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/862a958157c9b35089d298de0a8f487465d44ff250abbe77fe565b892ff2bdfd.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "863ce82554de77b85cb441ca72759bbe67c1fceaf2b1a3a82077da4ab1111dbb", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3e3b3265fd0e15d3dc2c05ccb7436992d397ebf6f93d0226940ab8df3e84a992", "generation_seconds_batch": 24.965252780006267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4419263005256653, "target_z": 0.010742186950725168, "ce": 6.0146708488464355, "genuineness": 4.174716949462891, "identity": 0.3286023736000061, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/863ce82554de77b85cb441ca72759bbe67c1fceaf2b1a3a82077da4ab1111dbb.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "864cb28a3a1293711a62f289db522a254d120702d1cd6bd23ca86257ba9551a4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "450baef85d0a2041872ca3fd4d100cc0cb1a61f2fa216b6f041fee4a4803d500", "generation_seconds_batch": 18.175639275927097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2894940376281738, "target_z": 1.34375007616611, "ce": 6.054384231567383, "genuineness": 4.8588056564331055, "identity": 0.7652972936630249, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/864cb28a3a1293711a62f289db522a254d120702d1cd6bd23ca86257ba9551a4.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "86c4b4a32827d5e00fb65fc57b75ec181e6dcaf47aeb5f345d4daefeb5418ffa", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "de35c48254301e1fc2b2c70138083db399dcada63aa7128dfe561240ce1daf85", "generation_seconds_batch": 22.71651874994859, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6921606063842773, "target_z": 0.404296931026033, "ce": 6.149696350097656, "genuineness": 4.570107460021973, "identity": 0.14305061101913452, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/86c4b4a32827d5e00fb65fc57b75ec181e6dcaf47aeb5f345d4daefeb5418ffa.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "86f9602d532a3e591832099814157c3e68366b1417047aa90df0f3a575aec5e6", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7bf48cefc216040960653e91c30c1acfcf39aaee4dd3caf82f40c6feeb1a98a5", "generation_seconds_batch": 17.625033886055462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2000802755355835, "target_z": 1.2031250322241236, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.7555553913116455, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/86f9602d532a3e591832099814157c3e68366b1417047aa90df0f3a575aec5e6.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "8730251a751751767e2d9dc9bd7277c51ec99e49c10483dec939136b3c518eea", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "91043a903bd13fb2753d6de69345cf0f3f19de31a6134fec78d3a170e4ad67e0", "generation_seconds_batch": 24.188729931018315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6685652732849121, "target_z": 0.36718748974686977, "ce": 6.022613525390625, "genuineness": 4.394378662109375, "identity": 0.6651208400726318, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8730251a751751767e2d9dc9bd7277c51ec99e49c10483dec939136b3c518eea.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "873c39ebe679a04738fe9889123f721b8ec469f00d940a90dfa7b9139c6326f2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1eec806edfaf1d9ef4ddfbf608cf6daffd29f8b9d944d850c43295f2d9afffc2", "generation_seconds_batch": 18.75591980200261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3342008590698242, "target_z": 1.4140625043941986, "ce": 6.062326908111572, "genuineness": 4.883909225463867, "identity": 0.5029798150062561, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/873c39ebe679a04738fe9889123f721b8ec469f00d940a90dfa7b9139c6326f2.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "8748f3ddf976311d45f0b20c45bfee3c79276131ccc27d6863777145d924bfd1", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d10d0b515f5a46954eb35400031ff373851d2a571893138409b596a04be3c575", "generation_seconds_batch": 22.084381639026105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0048038959503174, "target_z": 2.468750052730384, "ce": 5.903473377227783, "genuineness": 4.883909225463867, "identity": 0.7258718013763428, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8748f3ddf976311d45f0b20c45bfee3c79276131ccc27d6863777145d924bfd1.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "8899e8120617c40d2c6ca25e50cf14ddb5ea334911b771370e55c5d10e31e082", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c752bdf3e87da677f368975f8d4652e5af1ec2dc02e90d19048d78bac351da17", "generation_seconds_batch": 24.060074107022956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0659596920013428, "target_z": 0.9921875600540484, "ce": 6.324435234069824, "genuineness": 4.494794845581055, "identity": 0.37460917234420776, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8899e8120617c40d2c6ca25e50cf14ddb5ea334911b771370e55c5d10e31e082.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "88f1e56980fb447bd61d96ce3cc3f96396f7b395d658bcc7e70ede1942af3792", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a8dd684763f5148464fcb26538e23adfd87af05f9fcec6ed78bcd81a83c1d7fb", "generation_seconds_batch": 24.306740915053524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5478003025054932, "target_z": 1.7499999531285475, "ce": 5.414999485015869, "genuineness": 4.68307638168335, "identity": 0.7118215560913086, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/88f1e56980fb447bd61d96ce3cc3f96396f7b395d658bcc7e70ede1942af3792.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "892d90040cb9dc63931b584b238d497829bc3910079bb4ba4170f7ab9a77f68a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2e64760fcefe99efd233982dcacd8263d3e01003ab8f265912dfcd7a1329e707", "generation_seconds_batch": 25.372761911014095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19790132343769073, "target_z": -0.3730468665777859, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.6221140623092651, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/892d90040cb9dc63931b584b238d497829bc3910079bb4ba4170f7ab9a77f68a.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "8930987dc3560ff08a2d3341b080b77b114762bdeffb2762d2f086015b0c863a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5a946d5b0ea195707f0e690f4f46fa27aa7df1c45cff7bf459594d8e6b0b9826", "generation_seconds_batch": 26.353880246984772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4456518590450287, "target_z": 0.01660154034591507, "ce": 6.24500846862793, "genuineness": 4.218649387359619, "identity": 0.19735723733901978, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8930987dc3560ff08a2d3341b080b77b114762bdeffb2762d2f086015b0c863a.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "89e3a8c5f4e5f5306c881caeba7b5344bc61e9473e5e2acc67f62b90b1466f99", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "32035d9bbc5f2007399d7362bcaf3726008ceb77ebc84d0df7f6f8489fc5a641", "generation_seconds_batch": 16.701463784906082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.428581953048706, "target_z": 1.562499894539232, "ce": 6.427689552307129, "genuineness": 4.582659721374512, "identity": 0.349549263715744, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/89e3a8c5f4e5f5306c881caeba7b5344bc61e9473e5e2acc67f62b90b1466f99.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "8a37168318897797b8a71b5691335d3b9c04cd15170c3065d832419b0c818404", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f191b28138366b79c2202a4d36b9878aee53f76e955d5eb4027ed3c04883321a", "generation_seconds_batch": 27.463138798018917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06005513668060303, "target_z": -0.5898437624502295, "ce": 6.062326908111572, "genuineness": 4.394378662109375, "identity": 0.6118572950363159, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8a37168318897797b8a71b5691335d3b9c04cd15170c3065d832419b0c818404.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "8abdb4d5e44702f543f7d208909915dd905f7c5b75957c25367c4b565cbbc48a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a92de6d053a369019a440dfb1c389e8d747918f1836ede988fe0e0d69ba9162c", "generation_seconds_batch": 15.769160983036272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6868884563446045, "target_z": 1.9687501464732888, "ce": 5.967014789581299, "genuineness": 4.362998008728027, "identity": 0.5142251253128052, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8abdb4d5e44702f543f7d208909915dd905f7c5b75957c25367c4b565cbbc48a.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "8b1c3d013c83b9962641ed1eb0f525c8797abfb5b2e2089744c276e9c8d6e7d5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e198c75f25d80159b023de13d934792fd29b31789bf5d3e185166127018c5e91", "generation_seconds_batch": 22.940672132070176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.865715742111206, "target_z": 2.249999859385643, "ce": 5.796247482299805, "genuineness": 4.268857479095459, "identity": 0.44968220591545105, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8b1c3d013c83b9962641ed1eb0f525c8797abfb5b2e2089744c276e9c8d6e7d5.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "8b5b016da65049ca5f6caa1a4d8aec203078ceb1ba978096d028a8502cdaaec8", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e42c5569b07eca2d97ca5ae1e26ffcdb4b217c1b27e1d2ce80deb679240a9cb5", "generation_seconds_batch": 19.080621612956747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2745916843414307, "target_z": 1.320312475099541, "ce": 6.3641486167907715, "genuineness": 4.65797233581543, "identity": 0.6906239986419678, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8b5b016da65049ca5f6caa1a4d8aec203078ceb1ba978096d028a8502cdaaec8.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "8b849938828d4f4bae275760c8f70315b7daa68b802caa34c211a6564600df1a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2631c9ff93d96e2bffc332cf5bab77d0ec94b0673903fc0619db27032c6e45c5", "generation_seconds_batch": 22.728787322063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.926871657371521, "target_z": 0.7734375541951168, "ce": 6.435632705688477, "genuineness": 4.419482707977295, "identity": 0.5942440032958984, "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_Longing/8b849938828d4f4bae275760c8f70315b7daa68b802caa34c211a6564600df1a.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "8c34febdd7081a4cbc4b16b6c824e3ebee7c54c37cb75266f49a881aae4e2a3d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "96f4fa16286381d7105255ad3aae4de8a3e19be97e79b802b4ccb989598fc6fb", "generation_seconds_batch": 21.54892024595756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7927510142326355, "target_z": 0.5624999882821369, "ce": 6.340320587158203, "genuineness": 4.457139015197754, "identity": 0.6498474478721619, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8c34febdd7081a4cbc4b16b6c824e3ebee7c54c37cb75266f49a881aae4e2a3d.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "8c680d9fe7d31fdaaba957bee04e4f3251bd63270f8a1989c49e250fe4d7e56c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2527376bd755d5fbfbca999bd7011af2fc351ecd55d0540a6542cc6064146e1d", "generation_seconds_batch": 24.69651811895892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8259763717651367, "target_z": 2.1874999648464106, "ce": 6.229123115539551, "genuineness": 4.507347106933594, "identity": 0.5179876685142517, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8c680d9fe7d31fdaaba957bee04e4f3251bd63270f8a1989c49e250fe4d7e56c.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": "8c9a975c7c67868e9e275925a9faac420642bea6b0f8472a0dd6752a4d579f97", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a63f8f9e5b03dfbfef728e1f54f3cba68168dd41f21ab2bcc24ac53beec6165", "generation_seconds_batch": 27.05310004297644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.364005446434021, "target_z": 1.4609375190415275, "ce": 5.4666266441345215, "genuineness": 4.632867813110352, "identity": 0.7190126180648804, "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_Longing/8c9a975c7c67868e9e275925a9faac420642bea6b0f8472a0dd6752a4d579f97.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "8cab7c3bb7a5139de0b21a6ec6b2aab738e2eab09b281e12809347c97749812b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "24a1dcc0db2222f83aa5a62158fad8ab036138d3f549938314d22bf93ee8b630", "generation_seconds_batch": 22.36954315705225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.865715742111206, "target_z": 2.249999859385643, "ce": 5.863759994506836, "genuineness": 4.293961524963379, "identity": 0.5110398530960083, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8cab7c3bb7a5139de0b21a6ec6b2aab738e2eab09b281e12809347c97749812b.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "8d7977b6dd4634ed03e7461b89074e0941b3cba23b8a16ca6398c323022bbb83", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "175321f1154b961485dd6ad6285a61b06bd69788d043d293cf7a83d12860519c", "generation_seconds_batch": 22.923228472005576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7629464864730835, "target_z": 0.5156250673777129, "ce": 6.229123115539551, "genuineness": 4.570107460021973, "identity": 0.6227988004684448, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8d7977b6dd4634ed03e7461b89074e0941b3cba23b8a16ca6398c323022bbb83.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "8e02d96070f5312bdb47fe3532bceb5786e6463d4053302642b214d238ca5814", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6050cd080e9913a02e277cfcfa646ee6c4b2bf64a1672c2b3b760c51d69b4a02", "generation_seconds_batch": 18.999206879991107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21901290118694305, "target_z": -0.3398437390145033, "ce": 6.141753673553467, "genuineness": 4.444586753845215, "identity": 0.7062301635742188, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8e02d96070f5312bdb47fe3532bceb5786e6463d4053302642b214d238ca5814.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "8e37ff6da16587adfc606db763472c93f89dcb68c38b7dbcc3241713ab62f270", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c12fa161e67813dfe406d41df3b63016fedc5c2bce231b5fc5d19e42510ebe37", "generation_seconds_batch": 16.79984718700871, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9815133213996887, "target_z": 0.8593749560580134, "ce": 6.197352409362793, "genuineness": 4.344170093536377, "identity": 0.32174384593963623, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8e37ff6da16587adfc606db763472c93f89dcb68c38b7dbcc3241713ab62f270.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "8ebc12c3b801d3ecab6b0f9d89e9279abc07df24a8b53fe01c9b891172ccccdc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b85b882a8713c0b598ba41262bc22e62e76628841e2c9f70bba4860e783397f1", "generation_seconds_batch": 22.299476418062113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0907968282699585, "target_z": 1.031250041012521, "ce": 5.411027908325195, "genuineness": 4.582659721374512, "identity": 0.6037374138832092, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8ebc12c3b801d3ecab6b0f9d89e9279abc07df24a8b53fe01c9b891172ccccdc.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "8f28bf579ce5ff3f3269d724f62decb0bc50202770a0250b644f84f408db578a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "feff44a54a33cbef5f679c812415c9e7d5e164f0cdd26b0117234f190da1e198", "generation_seconds_batch": 19.16498312400654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6164072751998901, "target_z": 0.2851562609854967, "ce": 5.990842819213867, "genuineness": 4.532451152801514, "identity": 0.731966495513916, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8f28bf579ce5ff3f3269d724f62decb0bc50202770a0250b644f84f408db578a.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "8fac7fe2f177ef8b664e817605ceb0353f066f826a903615844371aad6a95b28", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "37ad621382bc0dfeeb1db401106b59195a4596d577ddd5e67f0f8acda46d3114", "generation_seconds_batch": 18.999206879991107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22894775867462158, "target_z": -0.3242187419439691, "ce": 6.23706579208374, "genuineness": 4.632867813110352, "identity": 0.6808079481124878, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8fac7fe2f177ef8b664e817605ceb0353f066f826a903615844371aad6a95b28.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "8fb5d78f7dfc2d792d1ac7fecc5d034499c42bf566807e145b5198307f51afaf", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "387c77e4153b4ee4a6764c82797f47e22f14916ead06465ce9f62cb1a7e68cb7", "generation_seconds_batch": 19.31731666205451, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.956676185131073, "target_z": 0.8203124750995409, "ce": 5.720792293548584, "genuineness": 4.532451152801514, "identity": 0.16107489168643951, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8fb5d78f7dfc2d792d1ac7fecc5d034499c42bf566807e145b5198307f51afaf.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "8fdecb4ac67cce1bcef421357b0d8fe658d72c62eb7e0cc4e7bf82a0f6566660", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ad1ecb43a8517a30b576679504d74a3eced6f4bc5bd9c9ef93c26cc937dc9568", "generation_seconds_batch": 18.343926599016413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5723212957382202, "target_z": 0.21582025885415798, "ce": 5.95112943649292, "genuineness": 4.582659721374512, "identity": 0.2121012806892395, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/8fdecb4ac67cce1bcef421357b0d8fe658d72c62eb7e0cc4e7bf82a0f6566660.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "903aa052af4e2623aadb2bd9e5b1374a59f43edbf002444c56cca49860de1b49", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d3ddebafb31e32e6513889698bcca294d036f3d506530cfc9a4522777a63a87e", "generation_seconds_batch": 16.32508714508731, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.09576416015625, "target_z": 1.0390623872155675, "ce": 5.772419452667236, "genuineness": 4.770940780639648, "identity": 0.733981728553772, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/903aa052af4e2623aadb2bd9e5b1374a59f43edbf002444c56cca49860de1b49.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "90dc64187b4c52c1b8886c62334936cff84c4058e3613700d1d0b3b9fc16d65a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d53b0d22915f38f918963f668bfeed501b109bb029fc2fb8f110c4fe68f816a0", "generation_seconds_batch": 24.14028445398435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24385003745555878, "target_z": -0.3007812580560309, "ce": 6.260893821716309, "genuineness": 4.3504462242126465, "identity": 0.491771399974823, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/90dc64187b4c52c1b8886c62334936cff84c4058e3613700d1d0b3b9fc16d65a.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "91638c84618acca22bb1edfcf1a876b53ba49da7f9d447a08441ac55332eeb4f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9608c07deb117a6fec91c651ff98cf324316d4e3155817ed23744923cce83343", "generation_seconds_batch": 25.44910821702797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6620512008666992, "target_z": 1.9296874780290068, "ce": 5.673136234283447, "genuineness": 4.532451152801514, "identity": 0.6106940507888794, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/91638c84618acca22bb1edfcf1a876b53ba49da7f9d447a08441ac55332eeb4f.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "9215d582c1bef76ded2f1c0f4590ebcc021c4604f925ad501cafd60e89ffd5fe", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4880e2cd3a949ee6e4f8c2951823e175e12a97cd23f97766e4bd1404abe70bae", "generation_seconds_batch": 17.39469522202853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5875396728515625, "target_z": 1.8124998476677796, "ce": 5.629451274871826, "genuineness": 4.532451152801514, "identity": 0.5420283079147339, "hypothesis": "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_Longing/9215d582c1bef76ded2f1c0f4590ebcc021c4604f925ad501cafd60e89ffd5fe.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": "924b92b46ac941f56142f270e4e416d988f2fc5d982e4450616fc384724a7324", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b9a596983f492dc95c5f163bbc4c7c1ba6616f032a167be48f204b8878b80f8", "generation_seconds_batch": 21.474986686953343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.423614501953125, "target_z": 1.5546873608503757, "ce": 5.5817952156066895, "genuineness": 4.369274139404297, "identity": 0.4968607425689697, "hypothesis": "Las llaves están en la mesa de la cocina, miren el cajón y luego junto a la ventana llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/924b92b46ac941f56142f270e4e416d988f2fc5d982e4450616fc384724a7324.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "92d6d410f796ca87e4d0eda92819487e0d869bd76dfe87d3f9a7db7a21f9425f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2a04be9f6f4af5c3611807d25da0a87b3f20945c8e96cea3a19ca779579993e5", "generation_seconds_batch": 21.834817308932543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1802105903625488, "target_z": 1.1718750849545074, "ce": 6.046441555023193, "genuineness": 4.6705241203308105, "identity": 0.7176178693771362, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/92d6d410f796ca87e4d0eda92819487e0d869bd76dfe87d3f9a7db7a21f9425f.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": "931840ffa8e8047b1ea141e3a141f9fe224f7b08edb6bfbd8d7316889f094ac5", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2867c244051c2acb56f3da3df0ac2bd5fb208dec523ac4fb8d7010fbbe4eea68", "generation_seconds_batch": 18.15546289109625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1951128244400024, "target_z": 1.1953124985352672, "ce": 5.764476776123047, "genuineness": 4.607763767242432, "identity": 0.29435858130455017, "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_Longing/931840ffa8e8047b1ea141e3a141f9fe224f7b08edb6bfbd8d7316889f094ac5.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "932fbf4ec5830526125d0ae21c2a64cc6b0d71fd73f6877a2b1baa0b98c87a18", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "67cb54f25e43e2da905d44ebb1f139ae6f75825d2342df439e3106acddb540d6", "generation_seconds_batch": 24.800628641969524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9864807724952698, "target_z": 0.8671874897468698, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.29788413643836975, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/932fbf4ec5830526125d0ae21c2a64cc6b0d71fd73f6877a2b1baa0b98c87a18.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "9353471d375725facf0be846c88ee1c3033b2238b5ed0741ac88808a21da972b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "095cc6e9e6d748d99e13782919ffcddbcc36c8fb664de350390344dc07a2e64f", "generation_seconds_batch": 23.708867541048676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1255688667297363, "target_z": 1.0859375893487062, "ce": 5.919358730316162, "genuineness": 4.469690799713135, "identity": 0.3370693325996399, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9353471d375725facf0be846c88ee1c3033b2238b5ed0741ac88808a21da972b.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "93c38758600530773d7749e47116927f20a845da2aabd4c2f1c308d1bf9816cf", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d2e31a91258e9100ba939db2461794e5129261ffc98e3ee77286ef344e159a34", "generation_seconds_batch": 23.985028589027934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0808619260787964, "target_z": 1.015624973634808, "ce": 6.268836498260498, "genuineness": 4.469690799713135, "identity": 0.5312334895133972, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/93c38758600530773d7749e47116927f20a845da2aabd4c2f1c308d1bf9816cf.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "93f18b76870c30160dc9ad578b3c76d321e0a94600a25f772738fec9cf5ba3e9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "02d51766aeb496cf6a9347be883702cf13bc53d3dec935d5336929bc708b0c7f", "generation_seconds_batch": 26.813732582959346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4832236766815186, "target_z": 1.6484373901450333, "ce": 5.8875885009765625, "genuineness": 4.494794845581055, "identity": 0.532387912273407, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/93f18b76870c30160dc9ad578b3c76d321e0a94600a25f772738fec9cf5ba3e9.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "941437a5853960a55fefe63e6d4ce1db9a88b75b936fec79e81883428c43cf53", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9fcc8ed5eabada46ff21ab1625780e63a66eb86f53b84cc4f80213ee18b4b387", "generation_seconds_batch": 21.851447512046434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48073434829711914, "target_z": 0.07177734860192769, "ce": 6.348263263702393, "genuineness": 4.645420074462891, "identity": 0.4209083914756775, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/941437a5853960a55fefe63e6d4ce1db9a88b75b936fec79e81883428c43cf53.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "945d885d0354ced8b9d67118af249fb7c08ed1c22e5dbd9dc0eda18498e73ece", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9da05cc104bd45b5161150126723762f5d17c5b46feaa81e311a8f43f0c845fc", "generation_seconds_batch": 24.9926310289884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.263719767332077, "target_z": -0.2695312404792362, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.5632950663566589, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/945d885d0354ced8b9d67118af249fb7c08ed1c22e5dbd9dc0eda18498e73ece.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "945dc3e0bb745433618bc0837e0d2d3ffe8e7aa8918584e95cdaaec9df1baff4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "49d8ff78ba5d10462b33d9420ce3da810638020d15c3d389cdec717c4473fecd", "generation_seconds_batch": 21.851447512046434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14325958490371704, "target_z": -0.45898438561931343, "ce": 6.205295085906982, "genuineness": 4.300237655639648, "identity": 0.5296673774719238, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/945dc3e0bb745433618bc0837e0d2d3ffe8e7aa8918584e95cdaaec9df1baff4.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "94bdd06e1e943d93b92eb367e46407e95d684c1cca570d1892055c8b1d6c2d65", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c7fe50ff99ff630bde9d3408481f85fb4bfd0537098fd3f7a4914ab7b1fa0c1b", "generation_seconds_batch": 26.517449420993216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4593123197555542, "target_z": 0.03808596111881782, "ce": 5.935244083404541, "genuineness": 3.8546390533447266, "identity": 0.49435698986053467, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/94bdd06e1e943d93b92eb367e46407e95d684c1cca570d1892055c8b1d6c2d65.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "94bde3c5962cc590980b696034120fbc945dd748b94921bf100f221135da2ecc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "56fb217c7f4d477d9bd7e0e1c6a623f34a5670eca84d7aee15d853940b596c23", "generation_seconds_batch": 22.132505715009756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7862370014190674, "target_z": 2.1250000703071787, "ce": 5.871703147888184, "genuineness": 4.557555198669434, "identity": 0.6892163753509521, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/94bde3c5962cc590980b696034120fbc945dd748b94921bf100f221135da2ecc.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "9525399409e0739a564c3b6f9efff7065b92cbe3e150acc6f8f274cbe4d2aefc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6fff0ef652e6008839e963e18bab96c6af45287ac975fe94e9ddeff050ce6eb5", "generation_seconds_batch": 24.051298122038133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5776050090789795, "target_z": 1.7968751552616862, "ce": 5.919358730316162, "genuineness": 4.632867813110352, "identity": 0.8383182883262634, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9525399409e0739a564c3b6f9efff7065b92cbe3e150acc6f8f274cbe4d2aefc.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "955b1a4d0a6f205e3e4a26d05cc8e7869a7507080dfafeac3c3a467c7c9fce9a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "687b1e33461ce5f0a588f8d3a89489103053447122f28a58f0a16bdef4e75ed8", "generation_seconds_batch": 25.619577376986854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6362769603729248, "target_z": 0.3164062082551127, "ce": 6.109982967376709, "genuineness": 4.457139015197754, "identity": 0.596197247505188, "hypothesis": "De deur staat nog open. ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/955b1a4d0a6f205e3e4a26d05cc8e7869a7507080dfafeac3c3a467c7c9fce9a.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "959900c08f7079a9c1c73cd9e5e2be0421e141e1a5282ad26bf27540ef03c9d7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d4340233bd8f667fa0849f665f463c1a52c52b0a5b1e51c9303fc100e931b7ec", "generation_seconds_batch": 18.454971938976087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6660815477371216, "target_z": 0.3632812229024416, "ce": 6.316492557525635, "genuineness": 4.457139015197754, "identity": 0.621996283531189, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/959900c08f7079a9c1c73cd9e5e2be0421e141e1a5282ad26bf27540ef03c9d7.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "95bc607307ab6c149a017ce887d199fff625eb011f2c85173a884aa385876bba", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bba2391d61255740710e2749ec43d273d1c002fdae02f72843e9ad9d0e7e0687", "generation_seconds_batch": 17.107081543072127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9020344614982605, "target_z": 0.7343749794937395, "ce": 5.95112943649292, "genuineness": 4.632867813110352, "identity": 0.7024133205413818, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/95bc607307ab6c149a017ce887d199fff625eb011f2c85173a884aa385876bba.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "9607a06bc08d48d77cbbe0111253fbf7d72db1b454b92effe62ff7cd43cbffe0", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9177481c21a5ed585f43e9cea89bf409eab3e483b9e9d30d5464221fb4c4173e", "generation_seconds_batch": 18.175639275927097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2745916843414307, "target_z": 1.320312475099541, "ce": 5.95112943649292, "genuineness": 4.68307638168335, "identity": 0.6166326999664307, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9607a06bc08d48d77cbbe0111253fbf7d72db1b454b92effe62ff7cd43cbffe0.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "9649b278bc0cd93067a0584495e0f5821279b962b190b69f2e2369340d1b2fcc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c6b2aa89bbcc1ae6c99c26ad001e952f352329603c9522bd9527911501307e9b", "generation_seconds_batch": 25.684325636946596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2894940376281738, "target_z": 1.34375007616611, "ce": 5.990842819213867, "genuineness": 4.595211505889893, "identity": 0.6656749248504639, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9649b278bc0cd93067a0584495e0f5821279b962b190b69f2e2369340d1b2fcc.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "9655b87c97b2872b036210836201e27e2a3b20f2f560b6c9f40ba7f1bdc5ef8c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "80ca142ef95473900904729137413070f83f76e0f5eef1c943743558923b0884", "generation_seconds_batch": 21.724447590997443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0758945941925049, "target_z": 1.0078126274317614, "ce": 5.760505676269531, "genuineness": 4.532451152801514, "identity": 0.6719614267349243, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9655b87c97b2872b036210836201e27e2a3b20f2f560b6c9f40ba7f1bdc5ef8c.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "96daa671694b1bc362ac2d1f2b1b8657e3672783e86281908a0d520d431ad172", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8c7825f277d7e7125feac8991ae0f2ec20dab272451c1f2b33fb08c1b505ac1c", "generation_seconds_batch": 22.728787322063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.847392737865448, "target_z": 0.6484374838879382, "ce": 6.372091293334961, "genuineness": 4.557555198669434, "identity": 0.5330578088760376, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/96daa671694b1bc362ac2d1f2b1b8657e3672783e86281908a0d520d431ad172.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "973b77e61aa1f6211210c85a63fe765ce5716a03fe8f3f118f2454b66ef80831", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "662426a158a1afb381a64f2a226908a0f9f2d3015100b7e9c75b432488d7280a", "generation_seconds_batch": 25.183324287994765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7132721543312073, "target_z": 0.4375000117178631, "ce": 6.24500846862793, "genuineness": 4.168440818786621, "identity": 0.3887174129486084, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/973b77e61aa1f6211210c85a63fe765ce5716a03fe8f3f118f2454b66ef80831.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "97554e2c1fe423a07e6998a07c229759b7373183800b72a072a90a668bd645f0", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bd525f3e4da6ec8fedc9a49ab4453f1cc470b17abc5497182de842e39cceb091", "generation_seconds_batch": 24.274772215052508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5676701068878174, "target_z": 1.7812500878839732, "ce": 5.7128496170043945, "genuineness": 4.6203155517578125, "identity": 0.4785950779914856, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/97554e2c1fe423a07e6998a07c229759b7373183800b72a072a90a668bd645f0.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "978276726c745c12e8c03bacab06a452972d967a7aa000197d684521df020676", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "44e427d0b31800ee94fd2a7670861e6dfead8fab1ddd07fd7fb6fa01dda8b625", "generation_seconds_batch": 21.263523216941394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.542832851409912, "target_z": 1.7421874194396911, "ce": 6.38003396987915, "genuineness": 4.557555198669434, "identity": 0.41272270679473877, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/978276726c745c12e8c03bacab06a452972d967a7aa000197d684521df020676.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "97a57433bce6b44bd6076190b84b8060a01f9db2b0ff8c0413f25bc39380a688", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "79f514459fd1484e3263f2c36b82a7babef607739a32bb3aff5f6bc3a3fd5af1", "generation_seconds_batch": 20.23363814293407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.855781078338623, "target_z": 2.2343751669795493, "ce": 6.284721851348877, "genuineness": 4.607763767242432, "identity": 0.3752731680870056, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/97a57433bce6b44bd6076190b84b8060a01f9db2b0ff8c0413f25bc39380a688.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "97dc404dc72125941fddd98e7846ad67e3c1702297938c2080342f221009d84f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fb5c144a44f8b8653337c84063b05caa7187607839bede629acaca63f46263de", "generation_seconds_batch": 25.50411948899273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3292334079742432, "target_z": 1.4062499707053422, "ce": 6.078212261199951, "genuineness": 4.482243061065674, "identity": 0.5927268266677856, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/97dc404dc72125941fddd98e7846ad67e3c1702297938c2080342f221009d84f.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": "9950556fde93e27a6eb87b05979b5707cc8bb9bc0b7251a57523c1740e11ef14", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cde93c7dc8a34dcaa028e19b111d7c6854361127b48848c7cfbb5289dc9bf7ce", "generation_seconds_batch": 19.03077532001771, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.324265956878662, "target_z": 1.3984374370164858, "ce": 5.879645347595215, "genuineness": 4.607763767242432, "identity": 0.7371385097503662, "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_Longing/9950556fde93e27a6eb87b05979b5707cc8bb9bc0b7251a57523c1740e11ef14.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": "995a1c6dab2c91976aff6229b02df58dde9d1fd728267e632ce404770444a0d2", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c6ae04434812e9b9a6936dec0ce2029bfdea4216eb98fa8d70d9ec331d477498", "generation_seconds_batch": 21.6491453780327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2994288206100464, "target_z": 1.3593749560580133, "ce": 6.006728172302246, "genuineness": 4.545003414154053, "identity": 0.4343498945236206, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/995a1c6dab2c91976aff6229b02df58dde9d1fd728267e632ce404770444a0d2.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "996f0748d6eefa1bf4ed6ee78cde8719f188c4fab5a146f8570c125a244b538d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "87d8db06b218497bdc86fd7e504332168af5d9b3ed6be233618a5416861e96d1", "generation_seconds_batch": 24.690801520016976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3869740962982178, "target_z": -0.0756836154463559, "ce": 6.213237762451172, "genuineness": 4.532451152801514, "identity": 0.5084058046340942, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/996f0748d6eefa1bf4ed6ee78cde8719f188c4fab5a146f8570c125a244b538d.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "99889a2d68f908f39256a841eb676e1edc2108a0b857687920bd5304d70351b9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f0558e05174da4435e6a441c9d42fa4f56008b4a14b33e29243f7840d34176e0", "generation_seconds_batch": 27.49970280996058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4186471700668335, "target_z": 1.546875014647329, "ce": 5.673136234283447, "genuineness": 4.595211505889893, "identity": 0.5013382434844971, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/99889a2d68f908f39256a841eb676e1edc2108a0b857687920bd5304d70351b9.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "99a638571f9256d970b57bdff28873341d7926d46bb038cf5da50f2d6d36abe9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ea8c1e14ade1594c39538589f02ca8a3f2f30ecfd71988af25177785527a2cf1", "generation_seconds_batch": 22.19163362006657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8061065673828125, "target_z": 2.156249830090985, "ce": 6.205295085906982, "genuineness": 4.758388519287109, "identity": 0.7777363061904907, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/99a638571f9256d970b57bdff28873341d7926d46bb038cf5da50f2d6d36abe9.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "3cdec5ec7bbc55fc34751c09f9f211b85e8f8b27dee3112728c43d928c6c8a54", "generation_seconds_batch": 19.355546964914538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4136797189712524, "target_z": 1.5390624809584725, "ce": 6.356205940246582, "genuineness": 4.607763767242432, "identity": 0.39808741211891174, "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_Longing/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "9a182b5683ecb77ae439be3ae8da2487f4275e144aa38ac502c8033b1374512a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "341f2a1eb81f6fdbf6feab9dd8681520671d0ab69d0391b5bcf4c3fdf427a5d9", "generation_seconds_batch": 21.667178951087408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4816657304763794, "target_z": 0.07324217523286207, "ce": 6.229123115539551, "genuineness": 4.532451152801514, "identity": 0.7414303421974182, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9a182b5683ecb77ae439be3ae8da2487f4275e144aa38ac502c8033b1374512a.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "9a58ac676e3012e09f6a27e2461e08f1cdeb5b7a76954e125fc123b5fcb57505", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "36397eda58aa970647c58521de70e65efddf3b5c4fa92b681928d74643bc8643", "generation_seconds_batch": 26.20704464998562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8796810507774353, "target_z": 0.6992187653796953, "ce": 5.681078910827637, "genuineness": 4.6705241203308105, "identity": 0.14001664519309998, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9a58ac676e3012e09f6a27e2461e08f1cdeb5b7a76954e125fc123b5fcb57505.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "9a643f58c3d76c8f3788d8691fb32999624a8b9c19cf408a88cfe4823926ac4d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d67d71ae5fdcb5de9c29fbd11077ee33e822786c57e92c181ead2b1ede57c549", "generation_seconds_batch": 25.564892507973127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6785001754760742, "target_z": 0.3828125571245826, "ce": 6.340320587158203, "genuineness": 4.319066047668457, "identity": 0.18923251330852509, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9a643f58c3d76c8f3788d8691fb32999624a8b9c19cf408a88cfe4823926ac4d.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": "9a6b3cbefa9cfa1f30fa3ff7ed559fb959e086528a2894a738c24f5a978182eb", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8da1debbab3e62b3ebc95873705a33b41c0d64c4b1150ca32805b0e9f1853d35", "generation_seconds_batch": 16.778781992034055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9194204807281494, "target_z": 0.7617187536618322, "ce": 5.669164657592773, "genuineness": 4.174716949462891, "identity": 0.250309020280838, "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_Longing/9a6b3cbefa9cfa1f30fa3ff7ed559fb959e086528a2894a738c24f5a978182eb.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "9a99fe7b278fd52ad6bc62f3c4698eff18e93ef92ac22728e66aeeeff92beaae", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0a512f538e13668cd4b65595961780bf40b263c3c632f98809ef661d67dd223", "generation_seconds_batch": 20.23363814293407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.865715742111206, "target_z": 2.249999859385643, "ce": 5.998785495758057, "genuineness": 4.256305694580078, "identity": 0.4604077935218811, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9a99fe7b278fd52ad6bc62f3c4698eff18e93ef92ac22728e66aeeeff92beaae.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "9aca2204962ee102116dec4aaf6b13de141955e52038dbbca8c26440b7c174b0", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8bc55733d8f9fb67aadfda10eeb776736bb159801ced9baa153050a14e8c8992", "generation_seconds_batch": 18.508316360996105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8399416208267212, "target_z": 0.6367187770975584, "ce": 5.784333229064941, "genuineness": 4.168440818786621, "identity": 0.44516241550445557, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9aca2204962ee102116dec4aaf6b13de141955e52038dbbca8c26440b7c174b0.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "9ae116ef070937d6545817f195e7d63c9910d925ca087ffa89cfd7573a98c344", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c442f743c74f5cd63199e8acd501abfb78db99239f65034a081918f42ac194cc", "generation_seconds_batch": 24.758428222034127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9467413425445557, "target_z": 0.8046875014647329, "ce": 5.95112943649292, "genuineness": 4.7834930419921875, "identity": 0.646664559841156, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9ae116ef070937d6545817f195e7d63c9910d925ca087ffa89cfd7573a98c344.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "9b9fcfeac6dd7a6d1e4a9e985c38c16d660689a91f9dc7d051f6b7659c870e32", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7836a2202d36b076f66044bca76d52c962c814a78c6649f5d568399e99ca01c8", "generation_seconds_batch": 23.375367445056327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5493469834327698, "target_z": 0.17968752490045908, "ce": 5.903473377227783, "genuineness": 4.444586753845215, "identity": 0.5216315984725952, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9b9fcfeac6dd7a6d1e4a9e985c38c16d660689a91f9dc7d051f6b7659c870e32.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "af389e3fd6a327887fc395428fa71d210fc11b3d8ce0f240acbdebc7bcf2765d", "generation_seconds_batch": 18.782777938060462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015348285436630249, "target_z": -0.6601562375497705, "ce": 6.268836498260498, "genuineness": 4.432034492492676, "identity": 0.540371298789978, "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_Longing/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "heldout-es-2", "language": "es", "sentences": [ "La carretera gira a la izquierda tras el puente.", "Sigue... hasta la pequeña puerta de madera.", "Te esperaré al otro lado." ], "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-2", "key": "9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3", "bucket": "emo_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "80e988a5bf7e3c30d1173b514626d6413999b791a52a5d79a46e316672753fed", "generation_seconds_batch": 17.269259549910203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09482714533805847, "target_z": -0.5351562609854966, "ce": 6.046441555023193, "genuineness": 4.432034492492676, "identity": 0.47663742303848267, "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_Longing/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "9daa3eefe297da1240b61092343edc97aab99b0a2444c1b0ae90506c774bbb76", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "237b92fd95ed60cd3b5d5409d46114c0d2a55e4c5a4c5cf5d8222f6516af4ebd", "generation_seconds_batch": 23.029096418991685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4385168552398682, "target_z": 1.5781249619169448, "ce": 5.099277973175049, "genuineness": 4.143336772918701, "identity": 0.5368479490280151, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9daa3eefe297da1240b61092343edc97aab99b0a2444c1b0ae90506c774bbb76.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "9dbd6ad109b79c6a263852dad15490a6b3d9f2f12d092de46d1fc0e4ace19f15", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b4813c11f7562f725fad92db6c8d4dc2046398538a3d5ebbd564fa9ab3e7d090", "generation_seconds_batch": 20.230708951014094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4192624092102051, "target_z": -0.024902333954598812, "ce": 6.205295085906982, "genuineness": 3.6789097785949707, "identity": 0.35515689849853516, "hypothesis": "A door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9dbd6ad109b79c6a263852dad15490a6b3d9f2f12d092de46d1fc0e4ace19f15.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "9e10d7bbfd319155abd02da9c36164cf12af86aad3998ca5a73b007488c34f6a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "bbdec6d994108a270dd64bcb267d67865b91f3fa77ed264476ce323bdd235544", "generation_seconds_batch": 23.459479312994517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.736562728881836, "target_z": 2.0468751083902337, "ce": 6.046441555023193, "genuineness": 4.758388519287109, "identity": 0.819983184337616, "hypothesis": "J'ai trouvé la 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_Longing/9e10d7bbfd319155abd02da9c36164cf12af86aad3998ca5a73b007488c34f6a.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "9e71a84883921a217ff891e1960a1cd92d77c185fa1b2a291aeee08c6be5ec9f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e41788a652c20a7e004881e94fb13f4414d4ed2969d8dba73ae559b962f6e4b0", "generation_seconds_batch": 18.75591980200261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5130283832550049, "target_z": 1.695312592278172, "ce": 5.935244083404541, "genuineness": 4.7834930419921875, "identity": 0.45155709981918335, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9e71a84883921a217ff891e1960a1cd92d77c185fa1b2a291aeee08c6be5ec9f.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "9fea7e63aff6d3770d18eb5cafc6aba4b85d09b47ca4cf68c0858dd55fea58cf", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b57770bcfc087530a807c3b539338fcb1f3f96eea02881730b916f15b435b14c", "generation_seconds_batch": 21.528980186907575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.428581953048706, "target_z": 1.562499894539232, "ce": 5.990842819213867, "genuineness": 4.758388519287109, "identity": 0.6816766858100891, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/9fea7e63aff6d3770d18eb5cafc6aba4b85d09b47ca4cf68c0858dd55fea58cf.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "a04e105e3fb039a002db5fd9ad3cc897fa1cdcc04f1a985314bc99ce86e514a7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa895752a08edee11aa75d19caebd32df7adc9b62ccb3c8b8c8c4765f839d07f", "generation_seconds_batch": 24.8015517789172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0709271430969238, "target_z": 1.0000000937429048, "ce": 5.645336627960205, "genuineness": 4.3127899169921875, "identity": 0.6442422866821289, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a04e105e3fb039a002db5fd9ad3cc897fa1cdcc04f1a985314bc99ce86e514a7.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "a05add476fadb495092a922a4aa11617ad59f812ec23874da2622717c33c1c1b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c8718a15514df6b833c6eb4823e9b3e14a7db01dd4005bef07b72513a75a97de", "generation_seconds_batch": 23.727141625946388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5527677536010742, "target_z": 1.757812486817404, "ce": 5.538110733032227, "genuineness": 4.607763767242432, "identity": 0.8246932625770569, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a05add476fadb495092a922a4aa11617ad59f812ec23874da2622717c33c1c1b.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "a0d6f7f4ee494cdb5fe0e561cde60de8e93524f1a24272fbd8b92b6305e8874d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2579d8ddb9393d486f91d91ad29b6b13e97575e0ff96695334037d3056d09559", "generation_seconds_batch": 20.31204782309942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.627279281616211, "target_z": 1.875000117178631, "ce": 5.152891159057617, "genuineness": 4.425758361816406, "identity": 0.43057548999786377, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a0d6f7f4ee494cdb5fe0e561cde60de8e93524f1a24272fbd8b92b6305e8874d.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "a160308a8e85be3432ae96c623d3339af783cb492055717c153d84beefa08f09", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3441407562299e478f2766b4dbb68351dec5e7dfd00d3962e5b9c44dcdd44a02", "generation_seconds_batch": 22.72662109299563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2894940376281738, "target_z": 1.34375007616611, "ce": 5.605623245239258, "genuineness": 4.15588903427124, "identity": 0.5615082383155823, "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_Longing/a160308a8e85be3432ae96c623d3339af783cb492055717c153d84beefa08f09.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "a177f0d7f21a6a86478522a182e45566136d5e54c836524fd2c7979fd5ae4e89", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2e3fad336460494aca33a2ab6af2131cb3485af7536a39520a41dae47cef94b5", "generation_seconds_batch": 25.625678005977534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8573275804519653, "target_z": 0.6640624575227463, "ce": 6.141753673553467, "genuineness": 4.632867813110352, "identity": 0.6792541146278381, "hypothesis": "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_Longing/a177f0d7f21a6a86478522a182e45566136d5e54c836524fd2c7979fd5ae4e89.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "a1de5afac0b7478586dc483c967cf52a1fe2da91c72e10b99aac3aa094e1d08e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c208d5815a95334f6f13822f63fc3912280a20ba3cb8ae6a061fa0367e4bb4ad", "generation_seconds_batch": 23.740415074047633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6660815477371216, "target_z": 0.3632812229024416, "ce": 5.744620323181152, "genuineness": 4.356721878051758, "identity": 0.5775178670883179, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a1de5afac0b7478586dc483c967cf52a1fe2da91c72e10b99aac3aa094e1d08e.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "a2770c1aff5f489395cd3e037253d126d813c5ae65a1d9a2d0fee34d4fd81fbc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "94c2b7a21e28f25553adcd6262c14bf3a1b551d3a50c159603430ac26b2beb87", "generation_seconds_batch": 17.693163283052854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8349741697311401, "target_z": 0.628906243408702, "ce": 5.919358730316162, "genuineness": 4.494794845581055, "identity": 0.5870867967605591, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a2770c1aff5f489395cd3e037253d126d813c5ae65a1d9a2d0fee34d4fd81fbc.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "a2a9feebd8f60981524b1fd46cfae7be4f751a39f37b1c16430e7142bc4f0c00", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "477636b3fabedbb7453c96677263400e351ccd77f0646098ca01bc1cb8422f5e", "generation_seconds_batch": 22.40926380001474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7343837022781372, "target_z": 0.47070309240969327, "ce": 6.157639026641846, "genuineness": 4.7834930419921875, "identity": 0.6363016366958618, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a2a9feebd8f60981524b1fd46cfae7be4f751a39f37b1c16430e7142bc4f0c00.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "a30c2557577dc00dfd8c3e946874ac12fdd93f0e2dc632a0740dd58ad788c37a", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d53720fa8a881272fa9c937b3bbc52f27a0a2a4d596e253fe275daaa8f7554ef", "generation_seconds_batch": 20.680847611976787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8424253463745117, "target_z": 0.6406250439419866, "ce": 6.157639026641846, "genuineness": 4.7834930419921875, "identity": 0.7975605130195618, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a30c2557577dc00dfd8c3e946874ac12fdd93f0e2dc632a0740dd58ad788c37a.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "a3391de04ce38c79f9b40ae5bd5c6f4a81296a810b2d2ca0924fb6b491d50aa1", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c90e5ef235cceb89a61c5b32346d3d1fc6fd77de00e79c76ca4ff8f51c7ac47b", "generation_seconds_batch": 25.619577376986854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0898597240447998, "target_z": -0.5429687478029007, "ce": 6.006728172302246, "genuineness": 4.545003414154053, "identity": 0.7000159621238708, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a3391de04ce38c79f9b40ae5bd5c6f4a81296a810b2d2ca0924fb6b491d50aa1.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "a347e1b758a8d18b6d9db0816f6c1ef4ddc5bbf985670320b19aaeb2f652c54c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "64e468a714dc7dc2d1757ba48eaefd0700148a8d7d58941ecd4dcaa79aa4ef9c", "generation_seconds_batch": 16.27116123691667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9541924595832825, "target_z": 0.8164062082551127, "ce": 6.006728172302246, "genuineness": 4.607763767242432, "identity": 0.6013256311416626, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a347e1b758a8d18b6d9db0816f6c1ef4ddc5bbf985670320b19aaeb2f652c54c.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "a349dd493958ec44755757396d20d957ec72cccdd32355add18b600ed60f2e7c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fcc1ccee39b24eb2d208fe93efdf57d551d3570ed1b5637a27bd9d6f5520d1ef", "generation_seconds_batch": 17.03945005009882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0808619260787964, "target_z": 1.015624973634808, "ce": 6.117925643920898, "genuineness": 4.337893962860107, "identity": 0.6322233080863953, "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_Longing/a349dd493958ec44755757396d20d957ec72cccdd32355add18b600ed60f2e7c.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "a34b5456fab6a9d8d35d2f43f6147ef602bb50ea6cf7cfbefca5d8dbb55c390a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "921a66eb5511b73697be4c8bd2e7daddddb0243015539140da4c04d41063c9c0", "generation_seconds_batch": 18.807749736937694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4434843063354492, "target_z": 1.5859374956058014, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.7850037813186646, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a34b5456fab6a9d8d35d2f43f6147ef602bb50ea6cf7cfbefca5d8dbb55c390a.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "a381dc8fd3d48ae5cb1c758d0068f6dbc319eb3e5f9fe03c2274c8c085c815f1", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ee66a4b214c406eaf1884b746bf4c401548d3daac45b1280d6542166c926137d", "generation_seconds_batch": 24.062231678981334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.522963285446167, "target_z": 1.7109376596558847, "ce": 5.224375247955322, "genuineness": 4.582659721374512, "identity": 0.583185613155365, "hypothesis": "la puerta sigue abierta. he dejado tu abrigo sobre la silla. dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a381dc8fd3d48ae5cb1c758d0068f6dbc319eb3e5f9fe03c2274c8c085c815f1.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": "a3adcbce145c0b901d1efeaccdfd03b9386ca1b0db898d67791e449814978f33", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "50bd0aee087ac54bd5baf87bd74df9fa7997351c0b736549649af2d5b4fb6772", "generation_seconds_batch": 24.232879484072328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9914482235908508, "target_z": 0.8750000234357262, "ce": 5.601652145385742, "genuineness": 4.6956281661987305, "identity": 0.8119329214096069, "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_Longing/a3adcbce145c0b901d1efeaccdfd03b9386ca1b0db898d67791e449814978f33.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "a409c3ff5e30a5526dfbeec6e265caedd369e685e011cb2eb02b7fd43856f43e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c0c6da6ef8a236d7aeab1e350700aa1aba3194247ae4b4f06f8fc66b9e44666", "generation_seconds_batch": 18.56309156899806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6834675669670105, "target_z": 0.3906249970705342, "ce": 6.284721851348877, "genuineness": 4.607763767242432, "identity": 0.5481128096580505, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a409c3ff5e30a5526dfbeec6e265caedd369e685e011cb2eb02b7fd43856f43e.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": "a4b345a58cb1b4897d257ca24b184f3791c034483bf5a605d501ab686592e5d4", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "75050407b5de09d9105a6717243aa0dd44dee37495841a1f00306dc4d2add542", "generation_seconds_batch": 16.62595081795007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3043962717056274, "target_z": 1.3671874897468699, "ce": 5.4666266441345215, "genuineness": 4.532451152801514, "identity": 0.7278984189033508, "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_Longing/a4b345a58cb1b4897d257ca24b184f3791c034483bf5a605d501ab686592e5d4.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "a4d84a45c65dc4eae82b0fd85592c8344154678abcba9439f4904784f9990a0e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8838b84e4e780010c58761689e8ac34bd01f4e8b5ff16cbd935a5a4d6a437e5a", "generation_seconds_batch": 21.717292358982377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7455604076385498, "target_z": 0.4882811994667154, "ce": 6.022613525390625, "genuineness": 4.369274139404297, "identity": 0.3931655287742615, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a4d84a45c65dc4eae82b0fd85592c8344154678abcba9439f4904784f9990a0e.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "a5f1ae6819f484cf86927bb476689f491e6604ed2654080afc3fb38195cfab7c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c7bfa7ab2360f4342b61f4e7d9c350fbb132c02b2e4776740c46c41e373c1f31", "generation_seconds_batch": 25.123406919068657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4909796714782715, "target_z": 0.08789062902801545, "ce": 6.062326908111572, "genuineness": 4.632867813110352, "identity": 0.42639708518981934, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a5f1ae6819f484cf86927bb476689f491e6604ed2654080afc3fb38195cfab7c.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "a60fbf0ab9198ca2018d752a8efdff89070e0433064d14f4e9d00b6631158ea5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1af0a402143eaf811009aaa89fe813e852e26386a6055be6d1ae150fc8eb23ce", "generation_seconds_batch": 24.74502906599082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5030934810638428, "target_z": 1.679687524900459, "ce": 6.419747352600098, "genuineness": 4.413206577301025, "identity": 0.48554903268814087, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a60fbf0ab9198ca2018d752a8efdff89070e0433064d14f4e9d00b6631158ea5.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "a66a2347e54d2da422e7a83a01476a3ac995f8d0056629bd84a4524ae04f4903", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f43ab8707cd6c24a52b509fc61cbb57730914a286c4abceca252b1cb3c7f7ccd", "generation_seconds_batch": 24.938349273987114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9517087936401367, "target_z": 0.8125000351535893, "ce": 6.38003396987915, "genuineness": 4.532451152801514, "identity": 0.6709634065628052, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a66a2347e54d2da422e7a83a01476a3ac995f8d0056629bd84a4524ae04f4903.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "a67b975323b63694346be6db72f0fbd467a7ee4114ed659efd86103266f11fe7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "de1a01f0e80350c35f8f2fe29968b918b608b915140fa4e38dd05b92da2b7b0c", "generation_seconds_batch": 18.500119201955386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8771973252296448, "target_z": 0.6953124985352671, "ce": 5.974957466125488, "genuineness": 4.093128204345703, "identity": 0.38681137561798096, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a67b975323b63694346be6db72f0fbd467a7ee4114ed659efd86103266f11fe7.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "a6e6992d58adfeb27dc4cdbce7359a633ded65755623e3dcb8cd44e1ffab018e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7fdf0fce53efcc6b6a0eb61ac412464340b93669edf70f27f0ff0a8c41aa4a0c", "generation_seconds_batch": 21.900604802998714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08737599849700928, "target_z": -0.5468750146473289, "ce": 5.974957466125488, "genuineness": 4.557555198669434, "identity": 0.5951276421546936, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a6e6992d58adfeb27dc4cdbce7359a633ded65755623e3dcb8cd44e1ffab018e.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": "a6f8813d2452ebfdded8d53a116c12bda8daaf010280d3e5f6778d09e0123fc6", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "02d59b683e015a024d3eca2a914a1438d394f43705c6ca5cbd11354d67f0cd74", "generation_seconds_batch": 22.86511001805775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9188108444213867, "target_z": 3.906249876962437, "ce": 5.474569320678711, "genuineness": 4.457139015197754, "identity": 0.489501416683197, "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_Longing/a6f8813d2452ebfdded8d53a116c12bda8daaf010280d3e5f6778d09e0123fc6.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "a6fd7f8a180bdea761b0d550f45a44ba23d39d20f5f0ac26f256f6de2756fbae", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae0d2b9026b21c879dd62cdabf7ecec19445bbf29045a0c34e0deb8928ee9024", "generation_seconds_batch": 24.306740915053524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1504058837890625, "target_z": 1.124999882821369, "ce": 5.911416053771973, "genuineness": 4.6956281661987305, "identity": 0.6802284717559814, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a6fd7f8a180bdea761b0d550f45a44ba23d39d20f5f0ac26f256f6de2756fbae.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "a72b794f6c375318863b5db593784126bcf9b2e79e338509fe1aba32912fb3f2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c428c5fb74ff18e891baf4634c54c4f0a5a6c7b5926d5020c93ad6446fe91c7b", "generation_seconds_batch": 26.517449420993216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5493469834327698, "target_z": 0.17968752490045908, "ce": 6.308549880981445, "genuineness": 3.9173994064331055, "identity": 0.44045335054397583, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a72b794f6c375318863b5db593784126bcf9b2e79e338509fe1aba32912fb3f2.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "a734c6c2e749ad7a3fd5545e80f69fc62b20d8f1e39ef40bf238047d06fca073", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "344411d21d9dce60ced2f416bfc29ec2e84baf168d00418e510060dc83e52de4", "generation_seconds_batch": 26.143654199084267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16809675097465515, "target_z": -0.41992185778938856, "ce": 6.125868320465088, "genuineness": 4.105680465698242, "identity": 0.5651510953903198, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a734c6c2e749ad7a3fd5545e80f69fc62b20d8f1e39ef40bf238047d06fca073.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "a7c8a1210c6d16c5a16bfb01979960b90165ab4f1ef570c892d71810b615d1f2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e95e662782c68fc1037a20b77a44b1719aca9427137ef61a273fd2d64199a76f", "generation_seconds_batch": 18.681189083959907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.14047110080719, "target_z": 1.1093750029294658, "ce": 5.903473377227783, "genuineness": 4.532451152801514, "identity": 0.6635557413101196, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a7c8a1210c6d16c5a16bfb01979960b90165ab4f1ef570c892d71810b615d1f2.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "ef256dedd3df8d9e0ac111d578fe2a86bfd3af01e01a9acadad658095574fa14", "generation_seconds_batch": 18.696252972004004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005413413047790527, "target_z": -0.6757812580560308, "ce": 6.221180438995361, "genuineness": 4.300237655639648, "identity": 0.6291049122810364, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel hem even wanneer je even tijd hebt.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea", "bucket": "emo_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e65622ee20255be63d913e49d7c6d73658b3660faa7409920b7d92984493a84c", "generation_seconds_batch": 16.446668064105324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48477038741111755, "target_z": 0.07812500878839733, "ce": 6.324435234069824, "genuineness": 4.532451152801514, "identity": 0.7235648036003113, "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_Longing/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "aa3594897e1c81ad1715b0ffa00aa30d4406adb117793611e011a59dbeda99f2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d14881c83781dc105293062f593fd91d85dd2137b2ef51c323b5207e41ac7a9a", "generation_seconds_batch": 22.546284900978208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0609922409057617, "target_z": 0.984375026365192, "ce": 5.95112943649292, "genuineness": 4.425758361816406, "identity": 0.4800484776496887, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/aa3594897e1c81ad1715b0ffa00aa30d4406adb117793611e011a59dbeda99f2.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": "aa7179a72cfa3a5f72a2443858ba33bf177b9713f92fcd68b6d440bd8a8955aa", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ff0de4821f9cc55f007be95de54ec34e3c2e26d2650a610c10b4e35521758b6b", "generation_seconds_batch": 21.6491453780327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2944614887237549, "target_z": 1.3515626098549667, "ce": 5.756534099578857, "genuineness": 4.362998008728027, "identity": 0.3184181749820709, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las ze twee keer en legde mijn telefoon weg zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/aa7179a72cfa3a5f72a2443858ba33bf177b9713f92fcd68b6d440bd8a8955aa.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "aab85e854aec3bbb1ea27245df0c79007bc91a456af034ede2d512293b334cb8", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "382b2ad67aae357de4dddd8cbe8c0a381c33af32592735b8bd2d0239a5ccda4a", "generation_seconds_batch": 26.762310898979194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9690947532653809, "target_z": 0.8398437155787771, "ce": 5.4944257736206055, "genuineness": 4.494794845581055, "identity": 0.5519765019416809, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/aab85e854aec3bbb1ea27245df0c79007bc91a456af034ede2d512293b334cb8.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "ab3375aed2594946f279975f4796787ee8041575a116c2f41acdd8b7e7ec4c7d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b6a701ed915e53b34f97be672efacfab0444cbb24896a69f78f5f45dc035d692", "generation_seconds_batch": 25.044573568971828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8722299337387085, "target_z": 0.6875000585893155, "ce": 5.784333229064941, "genuineness": 4.18726921081543, "identity": 0.4531141519546509, "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_Longing/ab3375aed2594946f279975f4796787ee8041575a116c2f41acdd8b7e7ec4c7d.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "ab4b6e7254ac4fc863a1c13e165cc65b7c2472d2498cf050ddb82f72ddcab2e3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "335e85a4e5b32b9dc19e94637aeafc86e38890fcfeab8794596be3045e57bdf8", "generation_seconds_batch": 18.48456936806906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7017905712127686, "target_z": 1.9921873725682386, "ce": 6.221180438995361, "genuineness": 4.921566009521484, "identity": 0.8297044038772583, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ab4b6e7254ac4fc863a1c13e165cc65b7c2472d2498cf050ddb82f72ddcab2e3.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "b9e618a0bc93ab355b25a344f9640e70e42c6e742670a1d3bf9db1472b55819b", "generation_seconds_batch": 16.395330702071078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5685957670211792, "target_z": 0.2099609523304205, "ce": 6.459460258483887, "genuineness": 4.406930446624756, "identity": 0.4575992524623871, "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_Longing/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "abacd4811ae941569e230f17b0f97e97058b65615b0f976bd4bf1a172f680063", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0dd0ebc16b4bf2cb4508c4f6c4b6d591c16c749fce44e7d7f37cf21de4fc58c2", "generation_seconds_batch": 22.192881285911426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6871931552886963, "target_z": 0.39648439733717655, "ce": 5.9431867599487305, "genuineness": 4.645420074462891, "identity": 0.6935503482818604, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/abacd4811ae941569e230f17b0f97e97058b65615b0f976bd4bf1a172f680063.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "abcaa2950ef6f63317d9bcc93b86963a8a5a5de12e76d51af57ef7d58179e189", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1ea8b0da5b55dd9650c1bf71d6d0d970fc41d7f01f32cbdff7c3b4ac0aa4acfc", "generation_seconds_batch": 22.72662109299563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2944614887237549, "target_z": 1.3515626098549667, "ce": 5.550024509429932, "genuineness": 4.293961524963379, "identity": 0.5759528279304504, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/abcaa2950ef6f63317d9bcc93b86963a8a5a5de12e76d51af57ef7d58179e189.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "ac0c777a623d36fb887f8bd98ac040156cf71783cecad4ee9468b8c0910a627c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b57e0617823aaa894bd38ce8ee9b21eca46ee0d1630af6964b5b66f9bb51b2e2", "generation_seconds_batch": 22.83371040597558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6570837497711182, "target_z": 1.9218749443401502, "ce": 6.006728172302246, "genuineness": 4.432034492492676, "identity": 0.5053575038909912, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ac0c777a623d36fb887f8bd98ac040156cf71783cecad4ee9468b8c0910a627c.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": "ac2100d531cb54f9b7deaa3aa2ac970ab255d385b3a7aff02c53bc06d375cc59", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9eb6fb107f8d56aa4d8a3a992a8c724dcd0156459e625ab3270bc773d666a5c0", "generation_seconds_batch": 22.823023890028708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5754259824752808, "target_z": 0.22070313928114565, "ce": 6.022613525390625, "genuineness": 4.65797233581543, "identity": 0.5783157348632812, "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_Longing/ac2100d531cb54f9b7deaa3aa2ac970ab255d385b3a7aff02c53bc06d375cc59.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "acb0d77a069fb31822f254b849555e720b98d111573a85816f7bc2af72fd60c8", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "849099bbd294bcf35d20f68fc2e632add6524cee779e182fcf27091de622eb17", "generation_seconds_batch": 22.559324526926503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10724571347236633, "target_z": -0.5156250205062605, "ce": 6.038498878479004, "genuineness": 4.494794845581055, "identity": 0.5615934133529663, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/acb0d77a069fb31822f254b849555e720b98d111573a85816f7bc2af72fd60c8.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "acbbab90b0504c5ebb0813103067baf308ee0f7e12539e65371265f9431f7bd0", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "44ae3988a8b1319334d63b0544f85c817cdfe1c11d5120ac05d8504758f5406c", "generation_seconds_batch": 25.4729586369358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0858293771743774, "target_z": 1.0234375073236643, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.6432989239692688, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/acbbab90b0504c5ebb0813103067baf308ee0f7e12539e65371265f9431f7bd0.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "acc9defd1d9530e9b387ae7d20cf12b494117f90df5f45cd1c966868f2c62de3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2cc4d75a085fefedf077e7c6f917b74c02a7bb7115af08d3ac2bc7a5613f627c", "generation_seconds_batch": 22.368793018977158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8151044845581055, "target_z": 0.597656296139086, "ce": 6.316492557525635, "genuineness": 4.419482707977295, "identity": 0.6773508787155151, "hypothesis": "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_Longing/acc9defd1d9530e9b387ae7d20cf12b494117f90df5f45cd1c966868f2c62de3.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "acf160b863c201c641113e31cf1b6c947ad9ce57722c8496de78aa341e1762e3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3a64cf185c795da6ee5761aebee29b2313fb6403c4fc2543364742a6a2054d8e", "generation_seconds_batch": 17.040210095932707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32270798087120056, "target_z": -0.17675782476713794, "ce": 6.308549880981445, "genuineness": 4.457139015197754, "identity": 0.6730362176895142, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/acf160b863c201c641113e31cf1b6c947ad9ce57722c8496de78aa341e1762e3.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "adb994391940baaf8a1e4ec8a1f33917c21fd1bb68958781739b18f9d4185211", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "04b06bce723fa708e6f1d0eb52979a02c4a81807f9a7ff06625c41f9c4476590", "generation_seconds_batch": 22.77882079198025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9715784788131714, "target_z": 0.8437499824232053, "ce": 6.078212261199951, "genuineness": 4.319066047668457, "identity": 0.39978694915771484, "hypothesis": "The 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_Longing/adb994391940baaf8a1e4ec8a1f33917c21fd1bb68958781739b18f9d4185211.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "57c9146ad719f01394cb814b6bccde2ef65a7670aad0341e5996bfc44584a291", "generation_seconds_batch": 16.86920558894053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.047636568546295166, "target_z": -0.6093750029294658, "ce": 6.141753673553467, "genuineness": 4.381826400756836, "identity": 0.6547210216522217, "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_Longing/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.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": "ae0421c1c24e9cc1af7706150b74a1b81ccf3f78120ac2e82017a71cff569ee4", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9be0967f3558cca901f218a90f4e139d8b99d471e80663528f6d0529d9e4fe16", "generation_seconds_batch": 21.007708112942055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7244488596916199, "target_z": 0.45507811877488524, "ce": 6.125868320465088, "genuineness": 4.482243061065674, "identity": 0.46648794412612915, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier, naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ae0421c1c24e9cc1af7706150b74a1b81ccf3f78120ac2e82017a71cff569ee4.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "ea35fb47beb3a3b35921d46f7b15b391363bbe4b60400927a048767346a20f29", "generation_seconds_batch": 18.693396004964598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8498764634132385, "target_z": 0.6523437507323664, "ce": 6.403861999511719, "genuineness": 4.080576419830322, "identity": 0.25603723526000977, "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_Longing/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "ae5175245d0fed98bb5c1a143e2cc434c4c63d75c6ae124be39eb11e7afab88f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a6f418729932b12a1c8283f08f9c48401e7d425f6ec82b926a4b20091067ff57", "generation_seconds_batch": 22.717050199047662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.14047110080719, "target_z": 1.1093750029294658, "ce": 5.561938762664795, "genuineness": 4.3127899169921875, "identity": 0.6246072053909302, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ae5175245d0fed98bb5c1a143e2cc434c4c63d75c6ae124be39eb11e7afab88f.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": "ae821acc5e2334f4b4dee61571fc9b4c665aba28ef11de9ad970bba45c0d152a", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fa8ef377446670792718f50c8c0b4438f40f6e9cf6874c03676cd4b94631493", "generation_seconds_batch": 19.30538588494528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0436062812805176, "target_z": 0.9570313459400042, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.5187214612960815, "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_Longing/ae821acc5e2334f4b4dee61571fc9b4c665aba28ef11de9ad970bba45c0d152a.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "aefc81981dbac130c6a2348328cb35d12e038534fe2c366ea575db7c6d866341", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "26fbc7cb1033d87fc01c82c3fddc24496604a2815c4c284590dbd886f8f20544", "generation_seconds_batch": 27.231300791027024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9392902255058289, "target_z": 0.7929687946743531, "ce": 6.1894097328186035, "genuineness": 4.7081804275512695, "identity": 0.6693505048751831, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/aefc81981dbac130c6a2348328cb35d12e038534fe2c366ea575db7c6d866341.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "af0258927e04cf9d439480a2e4c9593d9aa207ede2079adf429726ef1a207fe3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5386451de77b484177a337b887476a488e0f5aa9f90463a0628e918502d56721", "generation_seconds_batch": 22.877571549033746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.537865400314331, "target_z": 1.7343748857508348, "ce": 5.919358730316162, "genuineness": 4.582659721374512, "identity": 0.8228545188903809, "hypothesis": "La porte est encore ouverte J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/af0258927e04cf9d439480a2e4c9593d9aa207ede2079adf429726ef1a207fe3.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "af8043b9906b254eb3676316716367d75344964cdb5c9d34a58a2fcc5ca3c6d5", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bb043bd337d1cd2991fb55834700a8d743bb8d6ce133839979dadf1dc0d8a7c0", "generation_seconds_batch": 19.581561313010752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2804848551750183, "target_z": -0.24316403302225062, "ce": 6.070269584655762, "genuineness": 4.557555198669434, "identity": 0.73907870054245, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/af8043b9906b254eb3676316716367d75344964cdb5c9d34a58a2fcc5ca3c6d5.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "afa21a668dae2786085240ac1dcadc71e8447feb2f3df3e38a6d72d7ae247b20", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "edb74796473c977004e29b3bb526d4df79fe3e17bb58b2d5a0b97d5451f426bb", "generation_seconds_batch": 21.961116733960807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8225556015968323, "target_z": 0.6093750029294658, "ce": 6.268836498260498, "genuineness": 4.143336772918701, "identity": 0.40615594387054443, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/afa21a668dae2786085240ac1dcadc71e8447feb2f3df3e38a6d72d7ae247b20.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "b01eaf57565217b37d1db7456c5ca96e07e7124565f7e1a8c3194dd74422a2f7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3b863851a7d39ec07e25e46f0354f6a80893c7ee7dd10cabbb4399d995a1e446", "generation_seconds_batch": 21.754530976060778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6670186519622803, "target_z": 1.9375000117178631, "ce": 5.911416053771973, "genuineness": 4.419482707977295, "identity": 0.2389770746231079, "hypothesis": "The door is still open. I've 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_Longing/b01eaf57565217b37d1db7456c5ca96e07e7124565f7e1a8c3194dd74422a2f7.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "b0ca974f32a229f1e136651061fdf69da0d7287a4efeedea201fb715c5fe3c3a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "160ac9ef62155eea64814813e0bcf35f2758415bceea29bd8c98aa5c0b00ce4b", "generation_seconds_batch": 21.78088195307646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6015049815177917, "target_z": 0.2617187536618322, "ce": 6.09409761428833, "genuineness": 4.319066047668457, "identity": 0.5232781171798706, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b0ca974f32a229f1e136651061fdf69da0d7287a4efeedea201fb715c5fe3c3a.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "b10fbd3cf76514f2b2ef16989c1d46b2f8ee15e91ed6f1380442048de7c5f452", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "146ed9697d34f6492132522566b44fe0ca3daa27595623f6eb7dcfdee4ac91dd", "generation_seconds_batch": 20.02037854702212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4440995454788208, "target_z": 0.014160147003873644, "ce": 6.41180419921875, "genuineness": 4.532451152801514, "identity": 0.583003580570221, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b10fbd3cf76514f2b2ef16989c1d46b2f8ee15e91ed6f1380442048de7c5f452.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "b1224764c98f989e2dbd0f2cd0fbc9c2e55ba4aedcf6d037bfe480e86eb9b9fa", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "92d26044938a6e1f0795dd9a56df58eae705a6fcaf7d1f6818604cae49f03ad9", "generation_seconds_batch": 26.844304302940145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7902673482894897, "target_z": 0.5585938151806135, "ce": 5.780362129211426, "genuineness": 4.632867813110352, "identity": 0.7963163256645203, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b1224764c98f989e2dbd0f2cd0fbc9c2e55ba4aedcf6d037bfe480e86eb9b9fa.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "b1bbb8fe035d111336333af3037a69b5bb1731cab65c6abd0c2180403ed243a4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f7d08828bb7c1c32fc707ea31cb9ee0e6c4991f7e5743a69435fe8a91a305850", "generation_seconds_batch": 25.365690799080767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0445432662963867, "target_z": 2.531249947269616, "ce": 6.157639026641846, "genuineness": 4.6956281661987305, "identity": 0.3214991092681885, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b1bbb8fe035d111336333af3037a69b5bb1731cab65c6abd0c2180403ed243a4.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "b1c7a88e4bf300f41cf2e229f7b5e79623b9f850b64a4d9fe11b3422fbe4685f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b501dc05b4ee00c4a6f62670b88926f764c4fe114118c370064e0bc0d5dd7cf1", "generation_seconds_batch": 18.406287388992496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0485737323760986, "target_z": 0.9648438796288606, "ce": 6.284721851348877, "genuineness": 4.758388519287109, "identity": 0.5343325734138489, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b1c7a88e4bf300f41cf2e229f7b5e79623b9f850b64a4d9fe11b3422fbe4685f.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "b1f6490a67fc95d5bf8689c88b2e23aef0eb30f7e97efaf5f6d26479baeba57b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "01e921c63f493e0b62f272e1c34a815c9d063126b5808fd18cf56f7570b2afec", "generation_seconds_batch": 24.75416525104083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.084282636642456, "target_z": 2.5937498418088483, "ce": 5.661221981048584, "genuineness": 4.582659721374512, "identity": 0.7745918035507202, "hypothesis": "J'ai trouvé la 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_Longing/b1f6490a67fc95d5bf8689c88b2e23aef0eb30f7e97efaf5f6d26479baeba57b.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "b24d56bde583ff5b04786495dbec8648b3beb814e25da61e069e79da459d1a68", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c7256bcc8656054dd34c1ddf032d9e185f6e216934b7be9ab854cb7110119a3c", "generation_seconds_batch": 23.70690181502141, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.772881269454956, "target_z": 0.531249947269616, "ce": 6.372091293334961, "genuineness": 4.369274139404297, "identity": 0.4664340615272522, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b24d56bde583ff5b04786495dbec8648b3beb814e25da61e069e79da459d1a68.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "b25a7c43bb9c57a9f1292254c54ff41bf325f84822549955b9e64dac23bc5722", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "52315564add086ee3191700feda927adcad040541ef3535d388bbe3ef9a6f195", "generation_seconds_batch": 23.740415074047633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5726375579833984, "target_z": 1.7890626215728298, "ce": 5.748591423034668, "genuineness": 4.482243061065674, "identity": 0.05826263502240181, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b25a7c43bb9c57a9f1292254c54ff41bf325f84822549955b9e64dac23bc5722.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "b2c0a5028ff643b942056282ac9e4ee2e28182a3f6d6c54adae1095932294526", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0517ec45b1052b5bc1e11128c38a7553fb44c7ebd292c1744ab04ab0f9eaf154", "generation_seconds_batch": 18.163537963991985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.254721999168396, "target_z": 1.2890625278299248, "ce": 5.609594821929932, "genuineness": 4.6203155517578125, "identity": 0.5498572587966919, "hypothesis": "La porte est encore ouverte, je posais ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b2c0a5028ff643b942056282ac9e4ee2e28182a3f6d6c54adae1095932294526.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "b325d2f46001fa89e53fb3f9c4d148cf36691598517b4142bd1bc244ed932fd5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6f79640a24951ada91735a08ed0cb55635c437bfb90861b5db94e5c138c29932", "generation_seconds_batch": 16.595432532019913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5478003025054932, "target_z": 1.7499999531285475, "ce": 5.982900142669678, "genuineness": 4.607763767242432, "identity": 0.2625054121017456, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b325d2f46001fa89e53fb3f9c4d148cf36691598517b4142bd1bc244ed932fd5.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "b355bb3ae4d184f3b1770da5df0988d1223ec4baafbba1078512caff82fa7d9e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6ec81f8946946c7407893c5feee9f2ba2e3b03590be689e2b0202405b268f2b1", "generation_seconds_batch": 16.79984718700871, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4549658000469208, "target_z": 0.03124999414106845, "ce": 6.09409761428833, "genuineness": 3.660081624984741, "identity": 0.5290218591690063, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b355bb3ae4d184f3b1770da5df0988d1223ec4baafbba1078512caff82fa7d9e.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "b363308995ff240d398a5a606321df46bf189bdead5dd69539bd34e1ea5c01ee", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "79c898225adecd66c8ae89bd083402e078e0c465c9654fee1321b7d399736a6c", "generation_seconds_batch": 25.365690799080767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.637214183807373, "target_z": 1.890625184556344, "ce": 6.165581703186035, "genuineness": 4.3881025314331055, "identity": 0.4556899070739746, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b363308995ff240d398a5a606321df46bf189bdead5dd69539bd34e1ea5c01ee.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": "b3aa865f0c55e337058ee33ea7d3c407b835437a897a9386766426cb0e4fba32", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6e956176dfca559066bc46917af3436c353437f8aa4a7075650bdf7540f29278", "generation_seconds_batch": 24.65904502104968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9169367551803589, "target_z": 0.757812486817404, "ce": 5.281959533691406, "genuineness": 4.394378662109375, "identity": 0.6664479374885559, "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_Longing/b3aa865f0c55e337058ee33ea7d3c407b835437a897a9386766426cb0e4fba32.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "cc6b2fd21cbd689b3b2e4aef60e4a870e98c7f0730691efac935ec81dc24d5b0", "generation_seconds_batch": 19.883663478074595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05757144093513489, "target_z": -0.5937499824232053, "ce": 6.308549880981445, "genuineness": 4.319066047668457, "identity": 0.5987293124198914, "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_Longing/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "b4a8c9014b10684e63426df0d51d7db09000f9f68349d8f4a0ba70fc7bb289a2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "11add77adefba5b034615ce120ee23003c5acee5fbbc2e347d4358e989cc8a2a", "generation_seconds_batch": 28.54226120596286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2696242332458496, "target_z": 1.3124999414106844, "ce": 6.006728172302246, "genuineness": 3.9801597595214844, "identity": 0.5626546144485474, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b4a8c9014b10684e63426df0d51d7db09000f9f68349d8f4a0ba70fc7bb289a2.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "b4fb582b77964559fcfd497564981061faeccba912fa5dcb4260bb2e0f9c04ae", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5ec11c3b5633ea150c1255846ca92b429f07c1fad14f96cc123c8637388585c9", "generation_seconds_batch": 23.083162856055424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3143310546875, "target_z": 1.382812369638773, "ce": 5.700935363769531, "genuineness": 4.268857479095459, "identity": 0.5447452068328857, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b4fb582b77964559fcfd497564981061faeccba912fa5dcb4260bb2e0f9c04ae.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "b56dd7c2358ed60916a1c8e97f5fb9b367fb61a3ac1476d26a50bf23bb069ba7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3b94bb837d56f42aab260c309a80164f08653513a7a5f4e1082015a35aa71d21", "generation_seconds_batch": 20.936479057068937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6536629796028137, "target_z": 0.34374998242320537, "ce": 6.046441555023193, "genuineness": 4.3127899169921875, "identity": 0.7436321377754211, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b56dd7c2358ed60916a1c8e97f5fb9b367fb61a3ac1476d26a50bf23bb069ba7.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": "b56e80a179ecec80d3990d9a68466b4244c42f83a543dc825131ec23acd0b6ec", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b42872dad16fbed277075c0181178c92a5a6805915b1e8e419c21b9d1ac51a7d", "generation_seconds_batch": 21.917784277931787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7430766820907593, "target_z": 0.48437493262228715, "ce": 5.617537498474121, "genuineness": 4.362998008728027, "identity": 0.1589662879705429, "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_Longing/b56e80a179ecec80d3990d9a68466b4244c42f83a543dc825131ec23acd0b6ec.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "b5ac0175524d41d2a97624f5f34b2528a23097dcbef592e41a019b422ecd8cc5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c024404738c32e33c005c48ca5e3c22630b6367dd72dd1dcc07698e9769374a1", "generation_seconds_batch": 27.051700858050026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06999000906944275, "target_z": -0.5742187419439692, "ce": 5.974957466125488, "genuineness": 4.494794845581055, "identity": 0.4482404291629791, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b5ac0175524d41d2a97624f5f34b2528a23097dcbef592e41a019b422ecd8cc5.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "b5d5c7b97e5fd2dc6f01cf618a8e26222a67a9901c77a99e7eb4974cd7536b6e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b54121e7009d9d7e1ae2b373b3d043d4e82a0dd4e215f390ab2d3e06d881836e", "generation_seconds_batch": 24.089473271975294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3391683101654053, "target_z": 1.4218750380830552, "ce": 5.506340026855469, "genuineness": 4.306513786315918, "identity": 0.480893075466156, "hypothesis": "Encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b5d5c7b97e5fd2dc6f01cf618a8e26222a67a9901c77a99e7eb4974cd7536b6e.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "b639d5ca849744929c65de713f6d3b3b7de022625c9b15a230b558e69281fac0", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4dd5d1a14b77424b71af576c41b24a0deba2bdc1bf7c4b91495fecb0c3468529", "generation_seconds_batch": 25.044573568971828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7703975439071655, "target_z": 0.5273436804251879, "ce": 5.752562999725342, "genuineness": 4.432034492492676, "identity": 0.5061048865318298, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b639d5ca849744929c65de713f6d3b3b7de022625c9b15a230b558e69281fac0.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": "b6f78a691d9bc5252b9b52d7ad58ec2a6dca773ca60f5fb029360eea2008bee3", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3ffdbfca25ccf889f5aeedbe49642a57daf1b6cd37e54e80a000d7ddbf66e8e6", "generation_seconds_batch": 16.560789759038016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6946442723274231, "target_z": 0.40820310412755634, "ce": 6.125868320465088, "genuineness": 4.093128204345703, "identity": 0.41194844245910645, "hypothesis": "I wrote the number on the envelope, read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b6f78a691d9bc5252b9b52d7ad58ec2a6dca773ca60f5fb029360eea2008bee3.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": "b71de76e9d276afa949059c9488f77c69ef79053e303fd8a5e1c461b918ea548", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e242022d96f9579065e150627f3f960e6e18ef96a9956a04d55f5de2d4759e2", "generation_seconds_batch": 26.019273624988273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5825722217559814, "target_z": 1.8046873139789232, "ce": 6.24500846862793, "genuineness": 4.400654315948486, "identity": 0.48549968004226685, "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_Longing/b71de76e9d276afa949059c9488f77c69ef79053e303fd8a5e1c461b918ea548.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "b75905e4310f135dc2f81b12d2a4e99d28628192899f143a7655982a4a9982fc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f79ab61d0e6fb4be0990e7104f7806b14df111b68a0c5421d381b9a49882e742", "generation_seconds_batch": 25.821646166965365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5207842588424683, "target_z": 0.13476564367534433, "ce": 6.197352409362793, "genuineness": 4.469690799713135, "identity": 0.7147061824798584, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b75905e4310f135dc2f81b12d2a4e99d28628192899f143a7655982a4a9982fc.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "b7f73a76449bcbaa14acfab70a5f6154d842e34558d7077044e6e1ef83f50215", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3bf1c4a22defcb0fb6d7784b8ad65e4bcfcbf3c5cf77b4160f6ad0b03bbd231d", "generation_seconds_batch": 23.966567054972984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.14047110080719, "target_z": 1.1093750029294658, "ce": 6.173524379730225, "genuineness": 4.720732688903809, "identity": 0.6759193539619446, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b7f73a76449bcbaa14acfab70a5f6154d842e34558d7077044e6e1ef83f50215.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "b805aaa57a986fb2c3559d6358c70cb48d4fee5dd9790f81ca794dfa860f5f17", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "69722492ea3597a7a9c991f22e6fbc14c062e1b49ad629aa9eba3184756593f4", "generation_seconds_batch": 25.83680769300554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0808619260787964, "target_z": 1.015624973634808, "ce": 5.7406487464904785, "genuineness": 4.293961524963379, "identity": 0.4918674826622009, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b805aaa57a986fb2c3559d6358c70cb48d4fee5dd9790f81ca794dfa860f5f17.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "b866e0d23d1f25a9037cf380e627cb71623aaebf1a6c2bf72c677f308a753ed5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d132cead5210c9667daed7fa872872ea30e12ceefc6a95a59e290ea4934d1b43", "generation_seconds_batch": 21.59007122600451, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4385168552398682, "target_z": 1.5781249619169448, "ce": 5.863759994506836, "genuineness": 4.645420074462891, "identity": 0.6056432723999023, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b866e0d23d1f25a9037cf380e627cb71623aaebf1a6c2bf72c677f308a753ed5.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "b8dcf9d866c496b76028fbfb40371dfa528c7c706d52f21b3415a06891ce5848", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d3c6ab8ddfb895a94a3baa0f498faf5461f147f2af38fcd2578e7f2955942f77", "generation_seconds_batch": 21.724447590997443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.205047607421875, "target_z": 1.2109373784271702, "ce": 5.998785495758057, "genuineness": 4.632867813110352, "identity": 0.7329384088516235, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b8dcf9d866c496b76028fbfb40371dfa528c7c706d52f21b3415a06891ce5848.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "b9041c0b9400e1c247f62c1d4c7c2a3791d008125b89983e5085e3a9d8458d5a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "10e255f7db3da61561aeb7de1d75f70ad33fb2deb2c4626cac38a5b0e7e0c19b", "generation_seconds_batch": 15.769160983036272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5627026557922363, "target_z": 1.7734375541951168, "ce": 6.125868320465088, "genuineness": 4.369274139404297, "identity": 0.3779647946357727, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b9041c0b9400e1c247f62c1d4c7c2a3791d008125b89983e5085e3a9d8458d5a.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "b9041ca21baf1ee82bd4f272b2d89a8405d0a6ad5dc4439fe03bf3690f9edcd6", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5dae3ee20db3a4c96886f76163b5aadc03d3097bc99670c9056f6ca81cae234f", "generation_seconds_batch": 24.395739836036228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9914482235908508, "target_z": 0.8750000234357262, "ce": 5.772419452667236, "genuineness": 4.557555198669434, "identity": 0.22772787511348724, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/b9041ca21baf1ee82bd4f272b2d89a8405d0a6ad5dc4439fe03bf3690f9edcd6.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "b90b2bee6854faf8508c924ec5d603ffed1b24748185bfd9aab291c95ba6d235", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "49f18905d7c58e9f2e46b79c314473efd1be225abbc2875a59b52125d8d85f03", "generation_seconds_batch": 22.500964435981587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3916310667991638, "target_z": -0.06835938854877921, "ce": 6.0146708488464355, "genuineness": 4.770940780639648, "identity": 0.8427940607070923, "hypothesis": "La porte est d'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_Longing/b90b2bee6854faf8508c924ec5d603ffed1b24748185bfd9aab291c95ba6d235.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "ba00903273ee21c636a68c8ccbef04d6b54aa11966c35c94e049a5871d2fdab3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6cb8ed8a9883b8138a3ed59e371734e325ce388a232e03c3ae4ef67439bf4cc2", "generation_seconds_batch": 20.936479057068937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9368064999580383, "target_z": 0.7890625278299249, "ce": 6.086154937744141, "genuineness": 4.607763767242432, "identity": 0.6361813545227051, "hypothesis": "Ta porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ba00903273ee21c636a68c8ccbef04d6b54aa11966c35c94e049a5871d2fdab3.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "f55c55a847fd99e9dd052c9ba5c3ef9a123c773e527081ff7d0060aa48228d06", "generation_seconds_batch": 22.19087321299594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1954175978899002, "target_z": -0.3769531334222141, "ce": 6.157639026641846, "genuineness": 4.381826400756836, "identity": 0.5961230397224426, "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_Longing/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.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": "ba98c963db8d365e31cae40208341bfdd0fd85d21c1a7fb06167213ec8a5d484", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ec920d28b2aeb6f83aced70b86efb80a01e7f15751eb8039d0c81a970186866", "generation_seconds_batch": 19.676516829058528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0088341236114502, "target_z": 0.9023436101180092, "ce": 5.462655067443848, "genuineness": 4.6705241203308105, "identity": 0.6677953600883484, "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_Longing/ba98c963db8d365e31cae40208341bfdd0fd85d21c1a7fb06167213ec8a5d484.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "bac3bcda8d41f023d4a8f83a4219e885e48140235d515dab385abe7a0ac4821b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "513008f58acd3306316841894533909fbd5c3cc3071d4424832f560df5b61b8b", "generation_seconds_batch": 22.281035950989462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8796810507774353, "target_z": 0.6992187653796953, "ce": 6.38003396987915, "genuineness": 4.595211505889893, "identity": 0.6616330146789551, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bac3bcda8d41f023d4a8f83a4219e885e48140235d515dab385abe7a0ac4821b.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "baf6c872e6d8a65b5df384014c223407eab06b6c0372c1887b89a4e3ee3f7656", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "28d356a8eaca713f3ae0dc850df5622f10b493c948366a1878934b6c771e815a", "generation_seconds_batch": 23.497443866916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1106665134429932, "target_z": 1.0624999882821369, "ce": 5.696964263916016, "genuineness": 4.532451152801514, "identity": 0.13838204741477966, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/baf6c872e6d8a65b5df384014c223407eab06b6c0372c1887b89a4e3ee3f7656.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": "bb3d1eb685af9fa0580f38ed081729eacbe10e4bbb62bb82f3e3e1d2ee1989f5", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "811171fcc19a007aea5cf19442472938ae86e686ca6b5ec1bbd07af0d5a2087b", "generation_seconds_batch": 21.007708112942055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6921606063842773, "target_z": 0.404296931026033, "ce": 6.197352409362793, "genuineness": 4.469690799713135, "identity": 0.6537196636199951, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunchruin.", "wer": 0.14285714285714285, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bb3d1eb685af9fa0580f38ed081729eacbe10e4bbb62bb82f3e3e1d2ee1989f5.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "bb7d999b09349042a0acad3f000cead93727deac68c89418196929509984268d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0045af6fbe27605430ab675e3efe708573c5c3fcdec8230af9d0c5183751097c", "generation_seconds_batch": 21.834817308932543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4186471700668335, "target_z": 1.546875014647329, "ce": 5.903473377227783, "genuineness": 4.375550270080566, "identity": 0.7209206819534302, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bb7d999b09349042a0acad3f000cead93727deac68c89418196929509984268d.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "bba01de7cbeb8e89d3276bbba389707da436f2fe3c606a15397d643bc752d3ff", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fb8bfa00e3e6384a284aba857ba7e025a48ae35c677d0077164c384a1793cfce", "generation_seconds_batch": 24.520259308977984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1702756881713867, "target_z": 1.1562500175767947, "ce": 5.95112943649292, "genuineness": 4.344170093536377, "identity": 0.6730678081512451, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bba01de7cbeb8e89d3276bbba389707da436f2fe3c606a15397d643bc752d3ff.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "bc31ff4f4e89786f7ac142a6a22d030408bac0fa4df83c8e2a7b2b28418a210a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9eeb6221db1c1c8bcec20df43428d91bb72b483f3e439e8655dc99bd2e2da297", "generation_seconds_batch": 24.062231678981334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.084282636642456, "target_z": 2.5937498418088483, "ce": 5.522225379943848, "genuineness": 4.482243061065674, "identity": 0.3790518641471863, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bc31ff4f4e89786f7ac142a6a22d030408bac0fa4df83c8e2a7b2b28418a210a.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "bc490e7a8b6b9d8ac1bf5ab2a36361f1a606c2b02b504ffb34b62066f1701ec2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "43b6da5ba59c91254a9de7176dc7cc6870e337ba8f85e3fb901e4f0c06291ce7", "generation_seconds_batch": 18.711986919981427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3568590581417084, "target_z": -0.1230468900135121, "ce": 5.744620323181152, "genuineness": 4.482243061065674, "identity": 0.7267511487007141, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bc490e7a8b6b9d8ac1bf5ab2a36361f1a606c2b02b504ffb34b62066f1701ec2.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "bc8922351e65a78e9125d9f8a774f5bb77d28569194a8d124249b14c2af1cd74", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "03db1c5a16d76096eb5e51f5a45cde35678f56ecaf8cabb178f0903464567669", "generation_seconds_batch": 25.692835427937098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3043962717056274, "target_z": 1.3671874897468699, "ce": 6.070269584655762, "genuineness": 4.419482707977295, "identity": 0.7591004967689514, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bc8922351e65a78e9125d9f8a774f5bb77d28569194a8d124249b14c2af1cd74.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "bd15932e22359a1741837fb13a597df53f613a6964ce5cb790dd5e1bb750a26b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "527abad9af58ed53822dc5317d66a78ec04ba2640d7c6a5fe0359b8ea9ab227d", "generation_seconds_batch": 25.3383045559749, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.214982509613037, "target_z": 1.2265624458048832, "ce": 5.391171455383301, "genuineness": 4.507347106933594, "identity": 0.6966198682785034, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bd15932e22359a1741837fb13a597df53f613a6964ce5cb790dd5e1bb750a26b.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "bd17e2854fd61566a34e3168011a5e03c173b13a98a4109b79f1bf505b74273c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8bd7c85d24ce20e1cb2ef91c6115571749d34d1318ce2062803c66325573f4de", "generation_seconds_batch": 22.59443043509964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07495743036270142, "target_z": -0.5664062551265651, "ce": 5.982900142669678, "genuineness": 4.3881025314331055, "identity": 0.581298828125, "hypothesis": "Ik 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_Longing/bd17e2854fd61566a34e3168011a5e03c173b13a98a4109b79f1bf505b74273c.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "bd4a4e2e4e0473697ce59b9ceef9c062f797f50604f2c0b80e4d94e79bb1715d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6c3b971da657aa205aab0a28c525177f23860bbbc443b2043aa81b6bcf1eaea0", "generation_seconds_batch": 18.807749736937694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0147387981414795, "target_z": 2.484375120108097, "ce": 6.268836498260498, "genuineness": 4.833701133728027, "identity": 0.808192789554596, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bd4a4e2e4e0473697ce59b9ceef9c062f797f50604f2c0b80e4d94e79bb1715d.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "bd58a12fe35efcb212a2ca7b222361a8fd0cf4ce15b8a546395039efcbc59841", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2e16c6d47bb69af1a06d8a801f6485cac13a332cef56882ea3b55437519716a6", "generation_seconds_batch": 22.559324526926503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030250579118728638, "target_z": -0.636718730226106, "ce": 5.967014789581299, "genuineness": 4.457139015197754, "identity": 0.6742342114448547, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bd58a12fe35efcb212a2ca7b222361a8fd0cf4ce15b8a546395039efcbc59841.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "bd5999ea3cecc17ece125a50ea9299d4ee7cfe00ee8184b61f069e4cfe5e3a25", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7de578310fe0516321809a72d228b9b74b1fa6a34dd8771843cbd37dcd04581d", "generation_seconds_batch": 25.564892507973127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0336713790893555, "target_z": 0.9414062785622913, "ce": 6.133810997009277, "genuineness": 4.231201171875, "identity": 0.32734405994415283, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bd5999ea3cecc17ece125a50ea9299d4ee7cfe00ee8184b61f069e4cfe5e3a25.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "bd945f8537e920cb8bf3ce1839de04f1bbe8f2f30783af22997e0577fc0b4141", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "155e0e11313edad5f0ec168c6dc31ba8e098466dff9db26b8f6db2a1de39deac", "generation_seconds_batch": 24.21085099002812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.845846176147461, "target_z": 2.2187500996018366, "ce": 5.3514580726623535, "genuineness": 4.519899368286133, "identity": 0.6211070418357849, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bd945f8537e920cb8bf3ce1839de04f1bbe8f2f30783af22997e0577fc0b4141.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "be00132a3ea5223599de2cb71c265ec36cd80fd3c1a1928e00a4cda41ffc3caf", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b8957287251f3d46bbdeac01d518f54f16116ece25574314eb35b34facf4860f", "generation_seconds_batch": 18.711986919981427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.606472373008728, "target_z": 0.2695311936077838, "ce": 5.959072113037109, "genuineness": 4.607763767242432, "identity": 0.6583579182624817, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/be00132a3ea5223599de2cb71c265ec36cd80fd3c1a1928e00a4cda41ffc3caf.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "beac67b88b725894343596a6af0f3db60497cd81a80926b5e5dcc02edfa19430", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "00a73027a0e2ceef70b222b45270eb61469875c929326430fd62a4609d19e2bd", "generation_seconds_batch": 23.459479312994517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.965064525604248, "target_z": 2.4062501581911517, "ce": 5.998785495758057, "genuineness": 4.545003414154053, "identity": 0.83243328332901, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/beac67b88b725894343596a6af0f3db60497cd81a80926b5e5dcc02edfa19430.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": "bf3f90df7e46eb333acb0d8a41caf1293a0996937081a326ef7b0372f5a29758", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f0292c521dfb1f4893f17512bbffa9b29f479d3c355fd66867cc5b23290e33a", "generation_seconds_batch": 22.001615589950234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8026858568191528, "target_z": 0.578124961916945, "ce": 5.307773113250732, "genuineness": 4.444586753845215, "identity": 0.705620527267456, "hypothesis": "J'écris le numéro sur l'enveloppe, lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bf3f90df7e46eb333acb0d8a41caf1293a0996937081a326ef7b0372f5a29758.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "bf55075caf3ba29cdd0ac85f9eb4799ea1f4acb2f7b7cc95f72dd85adea0ebc7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7d50e12ec13520c75dd6be95d213bd2ce04715c6877e6c65b81b4d4a69f40774", "generation_seconds_batch": 24.758428222034127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4794924855232239, "target_z": 0.06982421517971359, "ce": 5.9431867599487305, "genuineness": 4.381826400756836, "identity": 0.6629115343093872, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bf55075caf3ba29cdd0ac85f9eb4799ea1f4acb2f7b7cc95f72dd85adea0ebc7.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "bf82d7d8cf7a87886772cfe2934dbb6dc1bf696de2debb5cdf63e466690ea16b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a9e8af6e26c6f679677d924592399e3db313039bd1dcc8c60785e5cfda742c0b", "generation_seconds_batch": 21.647322205943055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.100731611251831, "target_z": 1.0468749209044241, "ce": 6.141753673553467, "genuineness": 4.293961524963379, "identity": 0.45753028988838196, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bf82d7d8cf7a87886772cfe2934dbb6dc1bf696de2debb5cdf63e466690ea16b.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "bfecb64f5a757e5e1e18df4b8f993b06ef191d26a265f1553dee4c3e063c2f1a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "66208527a38c85938a43561a11a571775ab5c0f1be4be21f7eaf776b7ddbce47", "generation_seconds_batch": 21.622182330000214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4798029661178589, "target_z": 0.07031252197099332, "ce": 6.022613525390625, "genuineness": 4.545003414154053, "identity": 0.6938019394874573, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/bfecb64f5a757e5e1e18df4b8f993b06ef191d26a265f1553dee4c3e063c2f1a.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "c053528ba4e5bd5445015a713a323184dbe7ea00b8c74fac345e88cf6c798cd9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7618bbb755f49e2b4175b8abad682d0e1cedd630a906a96ae8cf95fc98e4f404", "generation_seconds_batch": 22.412062837043777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.319298505783081, "target_z": 1.3906249033276294, "ce": 6.038498878479004, "genuineness": 4.457139015197754, "identity": 0.6571844816207886, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c053528ba4e5bd5445015a713a323184dbe7ea00b8c74fac345e88cf6c798cd9.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "c07191a5bca4df2c08ed237dbacfda02ca53dca155a0ea006c47b9f222e84938", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e8044f3e81c5b63ac989289d7c619475d0066151c09974ad1855cdeb7fd3dd73", "generation_seconds_batch": 20.41669654904399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.760462760925293, "target_z": 0.5117188005332847, "ce": 6.117925643920898, "genuineness": 4.042920112609863, "identity": 0.4129391610622406, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c07191a5bca4df2c08ed237dbacfda02ca53dca155a0ea006c47b9f222e84938.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "c0fbc404e5e3c2940d5228bd786cb3e895636f4edeca9844f9aedfb421e39a72", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "018ba62190cce6cbc9bc86aa1b45dd549342675cbf9d5bbe47d8b9447b6bb395", "generation_seconds_batch": 26.143654199084267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12463173270225525, "target_z": -0.4882812463381678, "ce": 6.0305562019348145, "genuineness": 4.143336772918701, "identity": 0.630767822265625, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c0fbc404e5e3c2940d5228bd786cb3e895636f4edeca9844f9aedfb421e39a72.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "c1a5b2691b2802912481841b2b9a4747ba40edfb39bc858d6493be75e67be7c3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4322a8dd7eb17eb296824d56a269e8e1a8e6286ee71f61f58ff7f7b7566df054", "generation_seconds_batch": 25.45418433297891, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7961719036102295, "target_z": 2.1406251376848915, "ce": 5.895530700683594, "genuineness": 4.720732688903809, "identity": 0.7490791082382202, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c1a5b2691b2802912481841b2b9a4747ba40edfb39bc858d6493be75e67be7c3.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": "c286452352c142c08029d379c48b53588e74b9e8097273129c1aeb3b25e0fa05", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "456758e719ea363482836eb6306e181746f0d456fea68ff3e291d922e33cc9a2", "generation_seconds_batch": 19.54810117604211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7778487205505371, "target_z": 0.5390624809584724, "ce": 5.95112943649292, "genuineness": 4.337893962860107, "identity": 0.40503495931625366, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c286452352c142c08029d379c48b53588e74b9e8097273129c1aeb3b25e0fa05.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "c31e272e56bb1d7e49c42f457d39d17d3183cc09aa7aab61735954d922e554fa", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cf6ae6a3279f105deb779b042bb7e2265f47a12f2d08bff194f8907c897e7e7a", "generation_seconds_batch": 25.83680769300554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0411224365234375, "target_z": 0.9531248916097663, "ce": 5.80021858215332, "genuineness": 4.425758361816406, "identity": 0.333276629447937, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c31e272e56bb1d7e49c42f457d39d17d3183cc09aa7aab61735954d922e554fa.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "c339573a1d1bde3f8e65b9dafe4fbd3c8d05ab0d10a760967202aa773cf02b11", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6f711c1ac17e955692e737e849692f567fe28178b8f7a0f59f33ee8ca0e83a89", "generation_seconds_batch": 21.964383852900937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.974999189376831, "target_z": 2.4218748505972454, "ce": 5.665193557739258, "genuineness": 4.6705241203308105, "identity": 0.6743204593658447, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c339573a1d1bde3f8e65b9dafe4fbd3c8d05ab0d10a760967202aa773cf02b11.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "9b18643181b491f443fbf3cb627706b2c67cd9c915d85a72802c9e83ac011802", "generation_seconds_batch": 17.269259549910203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0898597240447998, "target_z": -0.5429687478029007, "ce": 6.054384231567383, "genuineness": 4.758388519287109, "identity": 0.7413058876991272, "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_Longing/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "62a79862761070c55e89f6b9edba08318c63fb920f64ccb632207e33d0e1ec69", "generation_seconds_batch": 18.782777938060462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022799432277679443, "target_z": -0.6484374838879382, "ce": 6.292664527893066, "genuineness": 4.482243061065674, "identity": 0.7741020917892456, "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_Longing/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "c4a72a332a318dac65b5f4199a8ef08ecb9e28853ca0f1e737cf6c5f5fdc364f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "79f6c15ed9ccf0b72fcdafc34f23b2f4d21f34a16866e01d5db1ab7390db92d8", "generation_seconds_batch": 32.261567434994504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.300975501537323, "target_z": -0.21093747217007514, "ce": 6.149696350097656, "genuineness": 4.68307638168335, "identity": 0.6558030843734741, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c4a72a332a318dac65b5f4199a8ef08ecb9e28853ca0f1e737cf6c5f5fdc364f.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "c4afc5280259b336fee8514df00000e599d89df03ad897f3cf5d724973c30cff", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5cae51d0e4d55498bc26917c09429a14526c771106871ac9a73483b808f7d920", "generation_seconds_batch": 22.49442011292558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08240857720375061, "target_z": -0.5546875014647329, "ce": 6.173524379730225, "genuineness": 4.532451152801514, "identity": 0.6717640161514282, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c4afc5280259b336fee8514df00000e599d89df03ad897f3cf5d724973c30cff.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": "c54804ccc3941f39f55bb39790f0fe799126fbdb64291cacb73fe875782220b6", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1f4dd9cb2efad706c76d15a08ddbb6258ea580b3e401598b2bbea0432f3d7560", "generation_seconds_batch": 20.75620990805328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6123769283294678, "target_z": 1.8515625161120617, "ce": 6.0305562019348145, "genuineness": 4.218649387359619, "identity": 0.5147228240966797, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c54804ccc3941f39f55bb39790f0fe799126fbdb64291cacb73fe875782220b6.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "c551032b7e4a7e77a5ec3070c58738a0aba4f2ae45c58eef908cbda971795ba2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d1a3bc72ac28b9a8dbce3a0910d1d5dd578219d7581d05ce17aa1448799169f3", "generation_seconds_batch": 20.807731081964448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6719861030578613, "target_z": 1.9453125454067195, "ce": 6.09409761428833, "genuineness": 4.507347106933594, "identity": 0.3089606761932373, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c551032b7e4a7e77a5ec3070c58738a0aba4f2ae45c58eef908cbda971795ba2.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "c5b5a80c0f2a0598f72ffeee1be71460e799ccd1f0ddba50c6b2ba3f3bfa076f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "59405c618dc42ef7cf3f2ae812069c4ffb76a6966e0aa99c72fa8440d16e51f8", "generation_seconds_batch": 28.112087878980674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4931585788726807, "target_z": 1.6640624575227463, "ce": 5.5539960861206055, "genuineness": 4.68307638168335, "identity": 0.6870650053024292, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c5b5a80c0f2a0598f72ffeee1be71460e799ccd1f0ddba50c6b2ba3f3bfa076f.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "c5f7872fe32edde7c3d119dfdaf46eb53565f3f89da626cd8afac1dbd1e831ba", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ef1936bea7e6c158be8a8cfd00aee0c931d9c1487661aeac737e8743e9dacc9b", "generation_seconds_batch": 17.107081543072127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9889644980430603, "target_z": 0.871093756591298, "ce": 5.704906940460205, "genuineness": 4.6956281661987305, "identity": 0.6020674705505371, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c5f7872fe32edde7c3d119dfdaf46eb53565f3f89da626cd8afac1dbd1e831ba.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "c6178a330e63d5543bbf4924b9102ab1a6e23cc895f34433e59de12cbe1bc062", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d468b9fc407b48e1f514d96c74d0eec57530d9bc48cfcf6a0a4a096769a14a02", "generation_seconds_batch": 17.640430091065355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8225556015968323, "target_z": 0.6093750029294658, "ce": 6.443574905395508, "genuineness": 4.545003414154053, "identity": 0.5774402022361755, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c6178a330e63d5543bbf4924b9102ab1a6e23cc895f34433e59de12cbe1bc062.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "c6cc9b74d72d4596b73f0ea8ccada4caec8fa0f7cd6e914c380885c2ab641b1a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c8dce118b36202f7493a72c36084124afdf65397b2cf13f0ccea9b15a15dcf15", "generation_seconds_batch": 18.758378549013287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1438918113708496, "target_z": 2.6874998711035056, "ce": 5.847874641418457, "genuineness": 4.645420074462891, "identity": 0.37770795822143555, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c6cc9b74d72d4596b73f0ea8ccada4caec8fa0f7cd6e914c380885c2ab641b1a.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "c6df4845b4617986ea3d8df391bfec9db269a3968de9a562b3efca2ba0869b08", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b341438477eb8c397fb82393c18a4df800622f3178d99b7526e2614e21016859", "generation_seconds_batch": 26.526121389004402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7182395458221436, "target_z": 0.44531245166381467, "ce": 5.967014789581299, "genuineness": 4.570107460021973, "identity": 0.6479751467704773, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c6df4845b4617986ea3d8df391bfec9db269a3968de9a562b3efca2ba0869b08.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "c736861d65f182949e500c91ac758a215a65567cd6879a92203c56211edb226d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7453c22258af510f0a70d917b63863a9f78791f24a348a7433617801c4cf1e4", "generation_seconds_batch": 22.717050199047662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.210015058517456, "target_z": 1.2187499121160268, "ce": 5.704906940460205, "genuineness": 4.337893962860107, "identity": 0.7155193090438843, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c736861d65f182949e500c91ac758a215a65567cd6879a92203c56211edb226d.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "c759d0c932ebee5bfeb0fe995790225801d4753a321f39d304802977d8554962", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "97861ec82d070b20bbcfe85f54424be1a00a73b16848f2136c0a7cfe0d9eae04", "generation_seconds_batch": 18.454971938976087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0684432983398438, "target_z": 0.9960936394126669, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.4831276834011078, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c759d0c932ebee5bfeb0fe995790225801d4753a321f39d304802977d8554962.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "c815456bdcbc25370aacc518dbc5bcf945163fc2536c0bd49b19fbb91e656011", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5402d85d71f790993a2d7f4a77dc4c61be5a9e4dfe3d08bdabcf21eba7653026", "generation_seconds_batch": 19.09108184208162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7182395458221436, "target_z": 0.44531245166381467, "ce": 5.692992687225342, "genuineness": 4.507347106933594, "identity": 0.3476894795894623, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c815456bdcbc25370aacc518dbc5bcf945163fc2536c0bd49b19fbb91e656011.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "9d518b55179893afe151f16220af2fa6d9a07d5e125b0fb0a22939bd1aecb0b8", "generation_seconds_batch": 16.86920558894053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15692001581192017, "target_z": -0.4375000117178631, "ce": 6.221180438995361, "genuineness": 4.425758361816406, "identity": 0.8009158968925476, "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_Longing/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "c82fed4d15c480531d3c69f04cafd62ecf4c56539b89c488246686b0a4a339fb", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "78baa418d45b0dd77dc9277e8ba463618540f7edee2a50c3fbebe94ba1aba5c1", "generation_seconds_batch": 25.026489630923606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.606472373008728, "target_z": 0.2695311936077838, "ce": 5.411027908325195, "genuineness": 4.2374773025512695, "identity": 0.5485315322875977, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c82fed4d15c480531d3c69f04cafd62ecf4c56539b89c488246686b0a4a339fb.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "e8c423c5d00c171f7eee063717da32330c5755c093b443d77333ede30be9d166", "generation_seconds_batch": 17.765595064964145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3686566948890686, "target_z": -0.10449221624538292, "ce": 6.372091293334961, "genuineness": 4.413206577301025, "identity": 0.2908918857574463, "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_Longing/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "c8d633ced5a6b45c7e53420f1f52b2f3b1b23890858e391e8af8b4569b93fc1e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "38de0bbb3d307620e564ce604a05ac89ba7e0b6ccbe16564101121e49187c957", "generation_seconds_batch": 24.9926310289884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10724571347236633, "target_z": -0.5156250205062605, "ce": 6.24500846862793, "genuineness": 4.482243061065674, "identity": 0.5796422362327576, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c8d633ced5a6b45c7e53420f1f52b2f3b1b23890858e391e8af8b4569b93fc1e.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": "c900b3be014a78bc3d8d6d7e408fa29b91fec7401149cf25f11e14b5850261e1", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fec80b5e5f89164068ac6cb96b3df2a1eafee1bc325330f93b1a3099fc80b917", "generation_seconds_batch": 16.50583780906163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2513011693954468, "target_z": -0.28906252782992486, "ce": 6.205295085906982, "genuineness": 4.6705241203308105, "identity": 0.4090717136859894, "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_Longing/c900b3be014a78bc3d8d6d7e408fa29b91fec7401149cf25f11e14b5850261e1.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "c9717fda17118267255c4aee49fd621ba44e43d45a011df1dcc2e222b48ff4ed", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bfc003350ada73fa332492ec8fb1992eb0951fd2f15f42a8b0c0e0fc5df7c1bf", "generation_seconds_batch": 25.07383648492396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3391683101654053, "target_z": 1.4218750380830552, "ce": 6.173524379730225, "genuineness": 4.595211505889893, "identity": 0.7759459018707275, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c9717fda17118267255c4aee49fd621ba44e43d45a011df1dcc2e222b48ff4ed.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "c98e6aa8a17fd449ac97dba4ceb8d29282cf19c56e4652562136b8cd23abb53d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "df3026b3dd487a92f79a3a850ee6fc688076d6675ccacc65d3a50d0ee086960d", "generation_seconds_batch": 27.231300791027024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9541924595832825, "target_z": 0.8164062082551127, "ce": 6.181467056274414, "genuineness": 4.833701133728027, "identity": 0.7036855220794678, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/c98e6aa8a17fd449ac97dba4ceb8d29282cf19c56e4652562136b8cd23abb53d.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": "c9f2db78ddcb15b39b5d70b1ec7eb1364041e8b8593d11531018e3f834a03703", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b70a690d37c6c49f1e20cba5a7363258668fc4000c990b5cf19858a6e79ce98d", "generation_seconds_batch": 17.1694810759509, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1752431392669678, "target_z": 1.164062551265651, "ce": 5.982900142669678, "genuineness": 4.545003414154053, "identity": 0.2809791564941406, "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_Longing/c9f2db78ddcb15b39b5d70b1ec7eb1364041e8b8593d11531018e3f834a03703.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "ca104c95cd91c76c6446767ca10497493dade7b020f7b20a539e0c68ce40b6fd", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5ec942449749b678e3e2323048a91381740cbd7e15c9e3a291b410fcda17a95b", "generation_seconds_batch": 21.90754825703334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38076481223106384, "target_z": -0.08544923568597401, "ce": 6.205295085906982, "genuineness": 4.557555198669434, "identity": 0.7489393353462219, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ca104c95cd91c76c6446767ca10497493dade7b020f7b20a539e0c68ce40b6fd.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": "ca3f4cb83412a6afa749fff1d66f5e1c6ea313789c790fb4e5b8397c30893c90", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c7857b7d576efd18a1b16c96a7b59ad2e11ba717902fccebd5105d6d6004738c", "generation_seconds_batch": 17.3947963709943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2398197650909424, "target_z": 1.2656251142491652, "ce": 5.474569320678711, "genuineness": 4.381826400756836, "identity": 0.5274418592453003, "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_Longing/ca3f4cb83412a6afa749fff1d66f5e1c6ea313789c790fb4e5b8397c30893c90.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "ca6d9e7d5c8798380c002ac70a8c79bd1a993ca5210e9a890bf6a49b92201c5a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e6b66c26ac282c9a9522aedb4e0709a1065b7c4c9c4a866896992069f9d6557d", "generation_seconds_batch": 24.96476655092556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3757973909378052, "target_z": -0.09326172250337803, "ce": 6.038498878479004, "genuineness": 4.595211505889893, "identity": 0.5847008228302002, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ca6d9e7d5c8798380c002ac70a8c79bd1a993ca5210e9a890bf6a49b92201c5a.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "cace49181d4ab84bc82ec1401c1f0411875df21e5a0120444675ad18457ea09a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9090e9559bd18f9fc4119e4b4220beb76f7de9feb43066d1b4f73cff8aee92c", "generation_seconds_batch": 23.1860169460997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3987774848937988, "target_z": 1.5156250673777127, "ce": 5.744620323181152, "genuineness": 4.65797233581543, "identity": 0.4404938220977783, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cace49181d4ab84bc82ec1401c1f0411875df21e5a0120444675ad18457ea09a.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "cae90eb9ac59528dea84d8f9bae0e0f0c289d3fe299fd0f4d5d03bc1b746c2cc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5eaeef3af6b7af81fc4ba03f86b3a0e193b6f9133af07fb510bbd7a52b849a32", "generation_seconds_batch": 25.096704630064778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5307191014289856, "target_z": 0.15039061731015232, "ce": 5.935244083404541, "genuineness": 4.519899368286133, "identity": 0.6459237337112427, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cae90eb9ac59528dea84d8f9bae0e0f0c289d3fe299fd0f4d5d03bc1b746c2cc.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "cb040c2117ae9d98ee917d03c16f2af2672ef478acabce66b9bc13d603cf3282", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "447c4c92ba0cc9088d403eb8f3429518b9ecfa31fe2e7bfe2f6513e6e3d785ca", "generation_seconds_batch": 25.099927076953463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.35903799533844, "target_z": 1.453124985352671, "ce": 6.109982967376709, "genuineness": 4.532451152801514, "identity": 0.6544924974441528, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cb040c2117ae9d98ee917d03c16f2af2672ef478acabce66b9bc13d603cf3282.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "cb18c006776419189fa11958dc241bc43d92fd512f740c58885b4140648a45aa", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "245fdd9d12bb5b658d2f16d16bd91562b08a08b3da2a09e99e04138ffea1cba7", "generation_seconds_batch": 24.90495303401258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45061931014060974, "target_z": 0.024414074034771492, "ce": 5.9431867599487305, "genuineness": 4.607763767242432, "identity": 0.5977553129196167, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cb18c006776419189fa11958dc241bc43d92fd512f740c58885b4140648a45aa.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "cbc91dba7c80a2e8ffc27f21d61e37a50895c7da4957ad4dca75dcdce6e8f12d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e8de572fd329ecc1c293550145c011aba7d2d6d23fec1584533bd1383bcd208", "generation_seconds_batch": 21.1760967860464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4037449359893799, "target_z": 1.5234376010665693, "ce": 5.903473377227783, "genuineness": 4.607763767242432, "identity": 0.5464413166046143, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cbc91dba7c80a2e8ffc27f21d61e37a50895c7da4957ad4dca75dcdce6e8f12d.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "cbd5f2bc68ece245a28c47bda53711bc2b2927e4c392792dcaedba235681c863", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f7b3596a3420eb88908377de36ae2b58b0f0aa6c80ed447fade2783b55d702d1", "generation_seconds_batch": 23.214471339946613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4981260299682617, "target_z": 1.6718749912116027, "ce": 5.6532793045043945, "genuineness": 4.519899368286133, "identity": 0.40536636114120483, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cbd5f2bc68ece245a28c47bda53711bc2b2927e4c392792dcaedba235681c863.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "cbd69c2da1731cf6b0085d55550c421d0bc93f311c800d4a7472f18e429a02bd", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "253a5af2ac38a5cf71f0c65562f3dabcecc7f291923bf4e76c5be5657d7ad718", "generation_seconds_batch": 18.913494226057082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6275839805603027, "target_z": 0.3027343680425188, "ce": 5.6254801750183105, "genuineness": 4.425758361816406, "identity": 0.40715599060058594, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cbd69c2da1731cf6b0085d55550c421d0bc93f311c800d4a7472f18e429a02bd.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "cbfde2bbc577d5031fabd86fd5504b92275defa012fdd33f4ff524a33a116796", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d4174aaa4148a267e28a5d047356f0c902052cdfe2e973bec1eb8eaa059aad3b", "generation_seconds_batch": 22.751727318041958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2199499607086182, "target_z": 1.2343749794937395, "ce": 5.736677646636963, "genuineness": 4.369274139404297, "identity": 0.41604751348495483, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cbfde2bbc577d5031fabd86fd5504b92275defa012fdd33f4ff524a33a116796.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "cbfec45b0c06a02dc782fbdab9165e75fac904d99ee227081e2c4820c536ec3a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ac93db844fbfaf3166689db4fa689f6af4c223ba70ddd0f3cf18b8d447f2ae20", "generation_seconds_batch": 25.627055373042822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09979459643363953, "target_z": -0.5273437272966403, "ce": 6.260893821716309, "genuineness": 4.532451152801514, "identity": 0.660362720489502, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cbfec45b0c06a02dc782fbdab9165e75fac904d99ee227081e2c4820c536ec3a.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "cc26ad12f142f736bbdca201992bb78736b0336521a490295fde9bf7223e2808", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b453cba005f5441b38db2dbc11104e05aa0a53970cb0bb11ce69be0452a03e9f", "generation_seconds_batch": 25.220996520016342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8771973252296448, "target_z": 0.6953124985352671, "ce": 6.372091293334961, "genuineness": 4.369274139404297, "identity": 0.5732079744338989, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cc26ad12f142f736bbdca201992bb78736b0336521a490295fde9bf7223e2808.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "cc27eb5f4f4acd3bcbc71499ed59d76bbb2ebe836cb7925c2fdeba56942ac58d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "71764e568f09a8175f5a0b9fde029f0b595e3077d73645637bfe00ea9091ae78", "generation_seconds_batch": 24.690801520016976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13456657528877258, "target_z": -0.47265627270335975, "ce": 6.268836498260498, "genuineness": 4.507347106933594, "identity": 0.4756697118282318, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cc27eb5f4f4acd3bcbc71499ed59d76bbb2ebe836cb7925c2fdeba56942ac58d.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "cc67c157a7a888ae3e7c0569310ddbadaae7f3631990a1b33b56914ad1e63a2c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0ab567c5d1dde4891804cac38f81812c0312a65e9577e02575b920a0c23f6197", "generation_seconds_batch": 16.701463784906082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8259763717651367, "target_z": 2.1874999648464106, "ce": 6.252951145172119, "genuineness": 4.595211505889893, "identity": 0.5368598103523254, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cc67c157a7a888ae3e7c0569310ddbadaae7f3631990a1b33b56914ad1e63a2c.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "cc7a72f439338632598de6f08dc72ad59fdfb6169457ae52b6aac03e0c0629df", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4c248fb81f1835bf8f75836040c1d2159cfaa376802a7c67c4e08ef5f458ef38", "generation_seconds_batch": 21.56126074597705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06750628352165222, "target_z": -0.5781250087883973, "ce": 6.09409761428833, "genuineness": 4.193545341491699, "identity": 0.7044302225112915, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cc7a72f439338632598de6f08dc72ad59fdfb6169457ae52b6aac03e0c0629df.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "cc98a55682d51e2b4aaa1c74e210987cfd88b3fd781bb1151aa33ff3f7cbdb0c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "92e9c20fd1426a319b04fd909f9c110b18401d0fdf3e8f50bef3eca54b0a3d48", "generation_seconds_batch": 24.800628641969524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9815133213996887, "target_z": 0.8593749560580134, "ce": 5.9431867599487305, "genuineness": 4.457139015197754, "identity": 0.43700534105300903, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cc98a55682d51e2b4aaa1c74e210987cfd88b3fd781bb1151aa33ff3f7cbdb0c.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "ccbed80babf9a962863b755e1bd38fc045b4eae4eb78f69a913d7ecd21a91e23", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0593f77a5f6843e909ce68d32f3238c564b0c36fcb8270c150dbf780edc1984f", "generation_seconds_batch": 25.692835427937098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1106665134429932, "target_z": 1.0624999882821369, "ce": 5.831989288330078, "genuineness": 4.331617832183838, "identity": 0.684796929359436, "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_Longing/ccbed80babf9a962863b755e1bd38fc045b4eae4eb78f69a913d7ecd21a91e23.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "cdc5b2c4bdfca4ef33be7279a3b9c31d59eb2d8f462deb6d49a4f108bac41896", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a0ab599247ac46b0c110e08b0fa49eff4e4a12aaa46fbc47f1bc718a78bda1d8", "generation_seconds_batch": 24.8962869719835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.423614501953125, "target_z": 1.5546873608503757, "ce": 5.744620323181152, "genuineness": 4.7834930419921875, "identity": 0.7864735126495361, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cdc5b2c4bdfca4ef33be7279a3b9c31d59eb2d8f462deb6d49a4f108bac41896.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "ce0ecc4b076702005e3052c5e74d02a5d39fae3df1cfa7269bb653d8d0bb743f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "53963d579ad48fe47104e4a21654a155f20e5f9f802d07bf2fdb14e60a270045", "generation_seconds_batch": 22.192881285911426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7828161716461182, "target_z": 0.5468750146473289, "ce": 6.284721851348877, "genuineness": 4.595211505889893, "identity": 0.5870405435562134, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ce0ecc4b076702005e3052c5e74d02a5d39fae3df1cfa7269bb653d8d0bb743f.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "ce1c14c82e1538ef41c22426096a6a9755769fbb0dc3b15ad5065db0a52c8d5f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c3bba92ab12c774fa10a4606f2b5326d6d62dcff74654f789a1a2168760f27de", "generation_seconds_batch": 23.92037905799225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6868884563446045, "target_z": 1.9687501464732888, "ce": 5.903473377227783, "genuineness": 4.758388519287109, "identity": 0.5560497045516968, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ce1c14c82e1538ef41c22426096a6a9755769fbb0dc3b15ad5065db0a52c8d5f.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "ce7d25e23f692fa72db34b09415c20c9be1041790f3828268f22ec4f2c8e5355", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d4805ac8ceb258b19156bcf8e790094d58b9f14ffc6f0174becfe3377a81a85f", "generation_seconds_batch": 23.991243668016978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1901453733444214, "target_z": 1.1874999648464106, "ce": 5.77639102935791, "genuineness": 4.243753433227539, "identity": 0.48415666818618774, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ce7d25e23f692fa72db34b09415c20c9be1041790f3828268f22ec4f2c8e5355.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "cec5a20778c207983326ef7bad53a44f084d34429a8f08af6015807bdc86d55d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6def458c946fa5c10cafba3517d3d2e54024cb093e1e75812ef3eebad5b48659", "generation_seconds_batch": 23.41422524303198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6909186840057373, "target_z": 0.402343703860914, "ce": 6.109982967376709, "genuineness": 4.7081804275512695, "identity": 0.3834056258201599, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cec5a20778c207983326ef7bad53a44f084d34429a8f08af6015807bdc86d55d.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "ced55859605b0da56efdd57f50b2ed2e8ea7d4874fd03cbe5e5e34f83d0e7c32", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "619e7bf02ceff0651d8400ad773c4df5da56a9a4dfdb6aeda112ddb9813b3da7", "generation_seconds_batch": 22.87846678402275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.364005446434021, "target_z": 1.4609375190415275, "ce": 5.593709468841553, "genuineness": 4.293961524963379, "identity": 0.503532350063324, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ced55859605b0da56efdd57f50b2ed2e8ea7d4874fd03cbe5e5e34f83d0e7c32.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": "cf54ecf76dd75f1bf1aaddcf95eb04ad89d98d73758b2e71644f5993e395428d", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa9910d7beb3753624289c4e58c391eb821fc01ef66d4245a58364e67a0cb032", "generation_seconds_batch": 18.275159658980556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0436062812805176, "target_z": 0.9570313459400042, "ce": 5.748591423034668, "genuineness": 4.833701133728027, "identity": 0.6985174417495728, "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_Longing/cf54ecf76dd75f1bf1aaddcf95eb04ad89d98d73758b2e71644f5993e395428d.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "cf5afcd3ae0ab690e966570d68ab90fb1520783f89a8d986d9cc9a024894b892", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c19f5a2d7d51a10c1db30af23d65503cedd579b585fa66cf2d84ff909a56a2ba", "generation_seconds_batch": 22.84741855307948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3233289122581482, "target_z": -0.1757812580560309, "ce": 6.165581703186035, "genuineness": 4.519899368286133, "identity": 0.46116387844085693, "hypothesis": "ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cf5afcd3ae0ab690e966570d68ab90fb1520783f89a8d986d9cc9a024894b892.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "0ed7a48e02a68726b17836b6f7b175f954b3937a31ca1326df5ff21524fbbdd0", "generation_seconds_batch": 16.633022353053093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15692001581192017, "target_z": -0.4375000117178631, "ce": 6.507116317749023, "genuineness": 4.545003414154053, "identity": 0.5484658479690552, "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_Longing/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "cf7aee60953b2bb575794d5daa906220f0e0c889f28637cc992d1b5db5f2c5a1", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7947505ef993c5efe784de7584099c8c4e8f65b0d372b133f96851bdf5af7de6", "generation_seconds_batch": 16.346255988930352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4186471700668335, "target_z": 1.546875014647329, "ce": 5.601652145385742, "genuineness": 4.595211505889893, "identity": 0.7904483079910278, "hypothesis": "La porte 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_Longing/cf7aee60953b2bb575794d5daa906220f0e0c889f28637cc992d1b5db5f2c5a1.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "cf8a9be3be199ce1d94aebcda8d9875bbcb7f6298add1ba963e5ed3546fa6b04", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "44ce8b012d3f239da05b0281c847c5f071e878f68fb9c96259374ab8a81331e5", "generation_seconds_batch": 25.30974334909115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0147387981414795, "target_z": 2.484375120108097, "ce": 6.475345611572266, "genuineness": 4.570107460021973, "identity": 0.3780860900878906, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cf8a9be3be199ce1d94aebcda8d9875bbcb7f6298add1ba963e5ed3546fa6b04.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "cf9a7090f852180a932e4d112217759c3edcc3ee531c8c583d043c148907c2de", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "75ae202fb673821f0cf00f322182ca207ce6ee8d9715716d38cd7e470192f36d", "generation_seconds_batch": 26.902615499100648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7207232713699341, "target_z": 0.4492187185082429, "ce": 5.585766792297363, "genuineness": 4.193545341491699, "identity": 0.4642721712589264, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/cf9a7090f852180a932e4d112217759c3edcc3ee531c8c583d043c148907c2de.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "d026027ca3a77b17c6eb3d6c3d604c9129f45a960b4ba1c0bcfe4b56a8afb7a8", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3c24cf2fa1c964e68c7238dc7975965db35da82ac3da7153bd2271d9ca3b1d49", "generation_seconds_batch": 21.931750096031465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7663671970367432, "target_z": 2.093749935551753, "ce": 6.300607204437256, "genuineness": 4.494794845581055, "identity": 0.41428452730178833, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d026027ca3a77b17c6eb3d6c3d604c9129f45a960b4ba1c0bcfe4b56a8afb7a8.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "d05154f1cb39730c0af59d0eb6f4433668449c076ad30b5149a34e8645f75889", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34792d7c43ad53bb37eddda5f654c833f78e735c69a1cbc45a3ea861a8c687df", "generation_seconds_batch": 24.72040598199237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4186471700668335, "target_z": 1.546875014647329, "ce": 5.657250881195068, "genuineness": 4.293961524963379, "identity": 0.7740935683250427, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d05154f1cb39730c0af59d0eb6f4433668449c076ad30b5149a34e8645f75889.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": "d0686e78a58427d2aff13ee931b86ccf40f9bfbdd26eadc1e3831fec8b0c45ef", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2d7fdf5657dcd0d40cc6c750c6cc1a482e2c283110be8e58b1e9339d2fa8da27", "generation_seconds_batch": 19.309784884913824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9020344614982605, "target_z": 0.7343749794937395, "ce": 6.141753673553467, "genuineness": 4.632867813110352, "identity": 0.657447338104248, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d0686e78a58427d2aff13ee931b86ccf40f9bfbdd26eadc1e3831fec8b0c45ef.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "d0d42c0e9cc39b3b21fcb916713a45bb82fbb1654913f1705503cf49b15914c4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b40060801569db43f4f636839013642946605f0ab2cdcd4676ba4070ac5a270e", "generation_seconds_batch": 24.86432381195482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0138015747070312, "target_z": 0.9101561438068656, "ce": 6.046441555023193, "genuineness": 4.268857479095459, "identity": 0.7253769636154175, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d0d42c0e9cc39b3b21fcb916713a45bb82fbb1654913f1705503cf49b15914c4.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "d0dc133ef84087fa24b1b2f4264134b4d1b64724871f3d688766b66ffb398c9c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1c2fc1f65cb896c1b5b61f84f03453a64537e340832f65ff9b36170f25273b82", "generation_seconds_batch": 22.018306251964532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0709271430969238, "target_z": 1.0000000937429048, "ce": 6.332377910614014, "genuineness": 4.432034492492676, "identity": 0.33226439356803894, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d0dc133ef84087fa24b1b2f4264134b4d1b64724871f3d688766b66ffb398c9c.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "d0fa9f4032ad5011f02848873f95d49ea1b04a2f69800904d22c7c2d58ec8ebe", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6be877262706a332bcba7464a756e59332b71aa05f5f709aaf943fcf450753e2", "generation_seconds_batch": 24.74502906599082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6223118305206299, "target_z": 1.8671875834897746, "ce": 6.3641486167907715, "genuineness": 4.65797233581543, "identity": 0.5143289566040039, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d0fa9f4032ad5011f02848873f95d49ea1b04a2f69800904d22c7c2d58ec8ebe.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "30188db2fc2e0f74872472a03b103f29f49b3d05f2b63051d4acfd75fc2a5f34", "generation_seconds_batch": 16.42544724792242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012864559888839722, "target_z": -0.6640625043941987, "ce": 6.427689552307129, "genuineness": 3.9676074981689453, "identity": 0.2865072786808014, "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_Longing/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "d1886a0cecde66552300f749111f709409392c71890224779b20a24fd8b41fe6", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "17613f8afc680c03cf6959a287229605537abe2659cf2735369a56748c215b92", "generation_seconds_batch": 26.29509677097667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8573275804519653, "target_z": 0.6640624575227463, "ce": 5.7684478759765625, "genuineness": 4.168440818786621, "identity": 0.41277188062667847, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d1886a0cecde66552300f749111f709409392c71890224779b20a24fd8b41fe6.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "d196511bb0cc3fe01b78ea4869277cfa64c627b9192a06a87eecd10b34dde22a", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b408909b821027134558f992dec6374d97c99c4fff2137dbb0384c0d9b5fcc66", "generation_seconds_batch": 21.239217801950872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25626862049102783, "target_z": -0.28124999414106844, "ce": 6.308549880981445, "genuineness": 4.519899368286133, "identity": 0.5773293972015381, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d196511bb0cc3fe01b78ea4869277cfa64c627b9192a06a87eecd10b34dde22a.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": "d1d3021d54a45c3bfbd3d40b91bb6f74648b8078c9686d59bb549262e0f87fb1", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ce104c6b2bbcc812f3fc3766fea4f91e997db18ab11a0841b3debf9358aeb98", "generation_seconds_batch": 16.50583780906163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14574331045150757, "target_z": -0.45507811877488524, "ce": 5.6334228515625, "genuineness": 4.2751336097717285, "identity": 0.4001244604587555, "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_Longing/d1d3021d54a45c3bfbd3d40b91bb6f74648b8078c9686d59bb549262e0f87fb1.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "d1e442cef1c4eff9a2a026d441e3fd516c708c3520803d341afb99b46cbdba93", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5b893265e005ed4c352515574ebe87a7aa5faa268507c615bb00feed22fc63f4", "generation_seconds_batch": 21.795656185015105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6251002550125122, "target_z": 0.29882810119809056, "ce": 6.054384231567383, "genuineness": 4.1998209953308105, "identity": 0.17170196771621704, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d1e442cef1c4eff9a2a026d441e3fd516c708c3520803d341afb99b46cbdba93.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "d227baa786c19a9c7b7522a18ddaf6b2ff23ff78ba3bae25edfda211b96ff6fb", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "842f3e901ac9955db08d770007b9ccb8756383a827c0518da56d47bafb0513de", "generation_seconds_batch": 22.042502900934778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5055714845657349, "target_z": 0.11083982956040014, "ce": 5.8875885009765625, "genuineness": 4.632867813110352, "identity": 0.7851648330688477, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d227baa786c19a9c7b7522a18ddaf6b2ff23ff78ba3bae25edfda211b96ff6fb.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "cc166771b4b2f49749678d9911002314b5f93d06a706e1515d10c12aac7054d4", "generation_seconds_batch": 20.83617404801771, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09234344959259033, "target_z": -0.5390624809584724, "ce": 6.300607204437256, "genuineness": 4.174716949462891, "identity": 0.816396951675415, "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_Longing/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "d237ada09c77c21175d5eab3e11eb013ceb503465ed164b5002c2a827125f9d7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bc300173c3d4e6ff3cbfdcfe6b71c4c6921ac5d4b3318a9ea75dfff93d8b432b", "generation_seconds_batch": 18.027537417947315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6673234105110168, "target_z": 0.3652343563246557, "ce": 6.1020402908325195, "genuineness": 4.532451152801514, "identity": 0.7111638784408569, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d237ada09c77c21175d5eab3e11eb013ceb503465ed164b5002c2a827125f9d7.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "d30b731c4a48bf08e096f6b9426efa1290950511da539238513bc4308c474024", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d61c2bd280beefb5e22955df0590d5a605986a1ca91022f02618d2cb8a06b8b9", "generation_seconds_batch": 21.89516553701833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9666110873222351, "target_z": 0.8359375424772537, "ce": 5.764476776123047, "genuineness": 4.432034492492676, "identity": 0.31085994839668274, "hypothesis": "ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d30b731c4a48bf08e096f6b9426efa1290950511da539238513bc4308c474024.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": "d349ddae88c8e86b5601bf84dde3f26eccb3cf6fe606daea7bde693fee559c46", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b669db09586102313060c907d7c57fe5c64ad73881d3d5de637dfcb005f6ba1", "generation_seconds_batch": 21.474986686953343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4981260299682617, "target_z": 1.6718749912116027, "ce": 5.5817952156066895, "genuineness": 4.287685871124268, "identity": 0.6074345707893372, "hypothesis": "Las llaves están en la mesa de la cocina, miren el cajón y luego junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d349ddae88c8e86b5601bf84dde3f26eccb3cf6fe606daea7bde693fee559c46.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "d353a37cb8a78f43baa87030827f7f98de20806defb5cc9dba5697ccd4ddc0ba", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "05308a9f3cead5d3d0e748ad57d8170e9775a55d62b8004b87e754371a01f400", "generation_seconds_batch": 28.54226120596286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0684432983398438, "target_z": 0.9960936394126669, "ce": 5.903473377227783, "genuineness": 4.306513786315918, "identity": 0.5208021998405457, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d353a37cb8a78f43baa87030827f7f98de20806defb5cc9dba5697ccd4ddc0ba.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": "d369e9dfc46119db5ef73488f2f079cd4d6029585f04d236d649585fb533e264", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9372876858d2593df6c11962d995b151a0039d15da8db7fa4f54c327c303e1d9", "generation_seconds_batch": 22.041905699996278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6139235496520996, "target_z": 0.28124999414106844, "ce": 5.685050010681152, "genuineness": 4.419482707977295, "identity": 0.3675144612789154, "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_Longing/d369e9dfc46119db5ef73488f2f079cd4d6029585f04d236d649585fb533e264.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "02d99c526b6d4fb36f4367a568eab64185936de14f5c189e2597b1352aeb777a", "generation_seconds_batch": 21.630562967038713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.029358595609664917, "target_z": -0.7304687595207637, "ce": 6.221180438995361, "genuineness": 4.545003414154053, "identity": 0.66701340675354, "hypothesis": "J'écris le numéro sur l'enveloppe, lis le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "d40c8216f0a76c30e1536881dca3cbd9f00a45e189215a5d7e92b1ce49467dea", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ff88c7d6879b5fdb2c5ce31476e964824caf90a89d922ec26c231f0354c10aa3", "generation_seconds_batch": 23.474023555056192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8061065673828125, "target_z": 2.156249830090985, "ce": 5.597680568695068, "genuineness": 4.570107460021973, "identity": 0.8407443761825562, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d40c8216f0a76c30e1536881dca3cbd9f00a45e189215a5d7e92b1ce49467dea.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "d4f17dd5f6aa9ca22f3ccfadb7434fb73e017aa156811339b7c92cf9410ef019", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2c7e66966a977d272f92dee65f6840758ff9303ab4319a27db3c14095bf1d200", "generation_seconds_batch": 24.031223485944793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.746497631072998, "target_z": 2.0625001757679464, "ce": 6.268836498260498, "genuineness": 4.457139015197754, "identity": 0.3736196458339691, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d4f17dd5f6aa9ca22f3ccfadb7434fb73e017aa156811339b7c92cf9410ef019.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "d4ffc1c07de7ac14b66923442775081b0ec2589579d3703caf63eb9e23496f05", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a824dda0030c2418005065abbac96979710364fa3fc8a8809a6e7f3404745822", "generation_seconds_batch": 24.317044410970993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.855781078338623, "target_z": 2.2343751669795493, "ce": 6.038498878479004, "genuineness": 4.645420074462891, "identity": 0.6546774506568909, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d4ffc1c07de7ac14b66923442775081b0ec2589579d3703caf63eb9e23496f05.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "d5520a78659a246d17eb6c004ce3dd14c0eee642bf42ec264cfeed3f28a99c97", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4abda6bb185fbe3fa10f17b0e70645768bc5d56dd1004ce92eb704b8451d15d6", "generation_seconds_batch": 23.70690181502141, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22894775867462158, "target_z": -0.3242187419439691, "ce": 6.157639026641846, "genuineness": 3.9299514293670654, "identity": 0.346605122089386, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d5520a78659a246d17eb6c004ce3dd14c0eee642bf42ec264cfeed3f28a99c97.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "d5ead1cd3105efd9d70aae2e3a89d034731fc2cc096d6464a5ae145cec0b4c65", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7c255872e63b33e37f0b1563ea4ffe0dbeb09f99ed407f39801f891895997077", "generation_seconds_batch": 24.188729931018315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6300677061080933, "target_z": 0.306640634886947, "ce": 5.998785495758057, "genuineness": 4.3127899169921875, "identity": 0.586848795413971, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d5ead1cd3105efd9d70aae2e3a89d034731fc2cc096d6464a5ae145cec0b4c65.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": "d6360bc4a3c61bab985117675ac05b14f479153ba0bdb6dbff1a72139a22c344", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b68dc7b7fab7d64be8893fbb7eb10b2e6e6889d9a1757f44080c0536bd8969b9", "generation_seconds_batch": 21.082567891920917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2696242332458496, "target_z": 1.3124999414106844, "ce": 5.418970584869385, "genuineness": 4.607763767242432, "identity": 0.4207518696784973, "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_Longing/d6360bc4a3c61bab985117675ac05b14f479153ba0bdb6dbff1a72139a22c344.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "d7b205508cf633fbf045a75ebd77779410e492143ed785f735df25d56801590b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cc0fff40c327f0e073debbdcc3eda9f8754ffc3aab1ef45b747df0bbbc75bad1", "generation_seconds_batch": 25.482424073969014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025283128023147583, "target_z": -0.6445312639149624, "ce": 6.1894097328186035, "genuineness": 4.595211505889893, "identity": 0.6081070899963379, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d7b205508cf633fbf045a75ebd77779410e492143ed785f735df25d56801590b.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "d7d886f13d29b16c6c70671abe22b9200018cbf86e87a6da21822964c93bbe80", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1374ab9f0c46b5a990825645d4838b02869c1c119c235e98e1e862a46f758a4a", "generation_seconds_batch": 26.27262021508068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0162854194641113, "target_z": 0.9140625981371034, "ce": 6.268836498260498, "genuineness": 4.582659721374512, "identity": 0.7307357788085938, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster, wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d7d886f13d29b16c6c70671abe22b9200018cbf86e87a6da21822964c93bbe80.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "d966e884ae88a2c5fb9ca7c6eb588681fdedbd880896c07c7d1304fc9bcbfb9e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6afdd22046b2b13dcd351d4a55f3b964608820e2941c34efb98c3921e82c5c07", "generation_seconds_batch": 25.193367805099115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5925071239471436, "target_z": 1.820312381356636, "ce": 5.80021858215332, "genuineness": 4.7081804275512695, "identity": 0.6011770963668823, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/d966e884ae88a2c5fb9ca7c6eb588681fdedbd880896c07c7d1304fc9bcbfb9e.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "da8cb880c77c51763cdd6dec97d22f0b175766b960af1dd4080d8d6a8785bc5f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83ed5b7e7b979b4f9c7cfd387f74384cd177c806ded28c5d2c299310f8325a33", "generation_seconds_batch": 23.478690747986548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3043962717056274, "target_z": 1.3671874897468699, "ce": 5.557967185974121, "genuineness": 4.570107460021973, "identity": 0.3862939476966858, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/da8cb880c77c51763cdd6dec97d22f0b175766b960af1dd4080d8d6a8785bc5f.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "dab0b811b5a0aa84c4b591222a69d76bf04a1b15080417af7713691ea21923ba", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a6d7c513b5e69d7ff9eb41f7b1607670b683e569023859eefa956e30d3474a50", "generation_seconds_batch": 22.789713975042105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8424253463745117, "target_z": 0.6406250439419866, "ce": 5.831989288330078, "genuineness": 4.149612903594971, "identity": 0.5215106010437012, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/dab0b811b5a0aa84c4b591222a69d76bf04a1b15080417af7713691ea21923ba.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "35e7a447bf690c7a2a5207abcd12e9e68a25ab2d2d41219864410dbb71fac341", "generation_seconds_batch": 16.395330702071078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36803579330444336, "target_z": -0.10546873608503757, "ce": 6.38003396987915, "genuineness": 4.168440818786621, "identity": 0.25657159090042114, "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_Longing/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "db24a2af6f11b253b956288152e21bbf3127cee5d3e30d6010060a8118fb3bb2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "79d31ebb9b1b4611bb0a670df3030a6eedb408c55fea3ea3b8c39643fd357d89", "generation_seconds_batch": 18.837989312014543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2596893310546875, "target_z": 1.2968748740329716, "ce": 5.927301406860352, "genuineness": 4.7332844734191895, "identity": 0.6538480520248413, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/db24a2af6f11b253b956288152e21bbf3127cee5d3e30d6010060a8118fb3bb2.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "db59f0e31cf075e782e16422f3ee3fc25661a31f9b297ccd3a4b091b4d629581", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9286ebc3b3d8fda6231b0f5d69fa41efb43bee398bc4cff74f72cda9ec85e58a", "generation_seconds_batch": 23.083162856055424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7803324460983276, "target_z": 0.5429687478029007, "ce": 5.935244083404541, "genuineness": 4.419482707977295, "identity": 0.3953602612018585, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/db59f0e31cf075e782e16422f3ee3fc25661a31f9b297ccd3a4b091b4d629581.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "dbbf9e2f18be890f00bc3e295d3810b245d5a31beed8639b5b5a2b5fc809341e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ca2c6f02ad408976085bddf84a27ff8bb71c78b2c02110e9c8e19f34d731c7d", "generation_seconds_batch": 24.289808382978663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7877836227416992, "target_z": 0.5546875483361853, "ce": 5.669164657592773, "genuineness": 4.545003414154053, "identity": 0.5785972476005554, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/dbbf9e2f18be890f00bc3e295d3810b245d5a31beed8639b5b5a2b5fc809341e.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "dbdc09cf1ba172467ee512b78b2ba53ead5b9d780b6d8919b50715638df30c81", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a90bf2290d734976197bf2a6d81ebb1353920768d2a33137c4b19f5c7e057cee", "generation_seconds_batch": 22.048509799991734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7961719036102295, "target_z": 2.1406251376848915, "ce": 5.605623245239258, "genuineness": 4.218649387359619, "identity": 0.5812102556228638, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/dbdc09cf1ba172467ee512b78b2ba53ead5b9d780b6d8919b50715638df30c81.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": "dbfb7b5dbb7a9ce804ae4ec17e79e28ff2f495203e4ef1a0db16d52ca149b678", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78aa0dd321997665d907bf42a9e10e05b9ee3223c02fc93aef8c5928fd34082e", "generation_seconds_batch": 24.665397631004453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8061065673828125, "target_z": 2.156249830090985, "ce": 5.871703147888184, "genuineness": 4.042920112609863, "identity": 0.507727861404419, "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_Longing/dbfb7b5dbb7a9ce804ae4ec17e79e28ff2f495203e4ef1a0db16d52ca149b678.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": "dc0e76ece7479f77053858fb976c78a14a358eec4ac49c0bffc33f3ecc986113", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa1e3be7f3b1795973c1bc75c3158c8a7884d1356c9fcb6d698651d71894e226", "generation_seconds_batch": 27.05310004297644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1339571475982666, "target_z": 2.6718751786974124, "ce": 5.764476776123047, "genuineness": 4.632867813110352, "identity": 0.7341034412384033, "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_Longing/dc0e76ece7479f77053858fb976c78a14a358eec4ac49c0bffc33f3ecc986113.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "dc349aff4b418acc9a4fb14479661cea55bfb384fe3427fa9d4a1d79287d5ae5", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "456ac89364ab7a483f6ab52f7e204d7fdd8ec849a4f329b63963d109ce6f7ee4", "generation_seconds_batch": 18.7919943400193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15692001581192017, "target_z": -0.4375000117178631, "ce": 6.23706579208374, "genuineness": 4.482243061065674, "identity": 0.6390447616577148, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/dc349aff4b418acc9a4fb14479661cea55bfb384fe3427fa9d4a1d79287d5ae5.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "dc4d0771fbdf6c911154e0b3b4815708b6e727ecd121082ae8f68795b10a1411", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ea825931c0607f14c15edd6b6244fab813822226826e0e03217af05965642e11", "generation_seconds_batch": 21.717247380060144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3888425827026367, "target_z": 1.5, "ce": 5.879645347595215, "genuineness": 4.532451152801514, "identity": 0.46739500761032104, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/dc4d0771fbdf6c911154e0b3b4815708b6e727ecd121082ae8f68795b10a1411.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "de07084508c4a5c4714eabfaf2aabbe9c231fd9fb7a919177aa3958a1b247607", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b8a52da54be2451e84ddb404b96b98dc72ce6aef4e79afcbee56c8450801b45b", "generation_seconds_batch": 29.907475398969837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.100731611251831, "target_z": 1.0468749209044241, "ce": 5.998785495758057, "genuineness": 4.331617832183838, "identity": 0.42482811212539673, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/de07084508c4a5c4714eabfaf2aabbe9c231fd9fb7a919177aa3958a1b247607.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "deaf6db29baf5365258a09f3807bde0910ca14c56a804b823e8325a40b9610ab", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "99b6d62dec87792faf20c7c3554492e7bc017ccf5f5b751e6854725942134457", "generation_seconds_batch": 27.707076077000238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1156339645385742, "target_z": 1.0703125219709932, "ce": 5.546053409576416, "genuineness": 4.645420074462891, "identity": 0.5517657399177551, "hypothesis": "He encontrado la cajita, estaba junto a la ventana, vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/deaf6db29baf5365258a09f3807bde0910ca14c56a804b823e8325a40b9610ab.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "deb037f85f7f97a69814d9a1ed5e1cefcd7eb5d249cbcc48d079b035b17ec4d9", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dee46878d7d0486c94bd5c83c1608ef595a92b6c4311ecb31d573c94e4319d7a", "generation_seconds_batch": 19.39797405397985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4593123197555542, "target_z": 0.03808596111881782, "ce": 6.419747352600098, "genuineness": 4.168440818786621, "identity": 0.276528000831604, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/deb037f85f7f97a69814d9a1ed5e1cefcd7eb5d249cbcc48d079b035b17ec4d9.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": "df7fde7f4eabb8fd245628e9ef7c429bbfc8fa8f3b4e9b546dff9440dd4ce749", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f621cc0d5aa61234c21b555e6c3ef1d1a9a4ca23d124d9533cb97df9bf66c06", "generation_seconds_batch": 25.27100669394713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0858293771743774, "target_z": 1.0234375073236643, "ce": 6.006728172302246, "genuineness": 4.469690799713135, "identity": 0.453130304813385, "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_Longing/df7fde7f4eabb8fd245628e9ef7c429bbfc8fa8f3b4e9b546dff9440dd4ce749.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "dfcb7548ff70a255e531b2d1be12d29de7d3a9539553bc4cf5dbec50475fc553", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "097053ff9acb7ce1d77ce591011bc69d42dbfe3311f5e3d558a8e6d5bc5c42dd", "generation_seconds_batch": 25.821646166965365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6337932348251343, "target_z": 0.3124999414106845, "ce": 6.229123115539551, "genuineness": 4.570107460021973, "identity": 0.5005711317062378, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/dfcb7548ff70a255e531b2d1be12d29de7d3a9539553bc4cf5dbec50475fc553.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "dfe6798e7bfdbd9466bff374b34b732526eb212bdd822a535b4db8a5b6adfa69", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4941a4f5f3a51be53d33652f77a94156e71e17aba35b3d06dfbe4b7bf29ab0ca", "generation_seconds_batch": 23.966567054972984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1206014156341553, "target_z": 1.0781250556598498, "ce": 6.1020402908325195, "genuineness": 4.632867813110352, "identity": 0.6654807329177856, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/dfe6798e7bfdbd9466bff374b34b732526eb212bdd822a535b4db8a5b6adfa69.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "e053d84367bd22f13d4f77d61b793c9b4570c483ca84caceb9f558a6792095c7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "855e6a6246c48e70ce4fe8be1c0d6e585361b22d0d0282731e3f54520d2ab90c", "generation_seconds_batch": 18.236051713931374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3491032123565674, "target_z": 1.437500105460768, "ce": 5.831989288330078, "genuineness": 4.036643981933594, "identity": 0.5227438807487488, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e053d84367bd22f13d4f77d61b793c9b4570c483ca84caceb9f558a6792095c7.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "e063eb72894c196972565d5833fbac4a204c726862e4ca380fa741ecd2fd77e4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d8a9fe9e03cc957c070619093a9b2b49e16bb88272b69ce956219ac5b0d7421e", "generation_seconds_batch": 22.789713975042105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9343227744102478, "target_z": 0.7851562609854966, "ce": 5.744620323181152, "genuineness": 4.406930446624756, "identity": 0.40337082743644714, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e063eb72894c196972565d5833fbac4a204c726862e4ca380fa741ecd2fd77e4.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "e192f9c50159e81ab4bfca81a25ea067151b954f4a91bbcbaf69d6a7cf7cfb6c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "50064f918da2b2790e9a863a7b2a8eb3edcda5715e0fc3c4a36a667ed5725a9c", "generation_seconds_batch": 16.627210465958342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3801438808441162, "target_z": -0.08642580239708107, "ce": 6.070269584655762, "genuineness": 4.557555198669434, "identity": 0.7032135725021362, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e192f9c50159e81ab4bfca81a25ea067151b954f4a91bbcbaf69d6a7cf7cfb6c.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "e1afb70486dc50ed12337b132f1d5be943aa6b2a2b9a1586ef1282f24b32cd50", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d455eec610475de2809851a52c982aa52fe076e2cc1d7ba6798df5b6e177d7fe", "generation_seconds_batch": 19.296857360983267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8771973252296448, "target_z": 0.6953124985352671, "ce": 5.990842819213867, "genuineness": 4.65797233581543, "identity": 0.6229531764984131, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e1afb70486dc50ed12337b132f1d5be943aa6b2a2b9a1586ef1282f24b32cd50.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "e1d6c26ef1383bd2c0f7a74150f4fdd11ce30a57851e64f1317613b73d48af13", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6ee08c227ad4d04951024f4066ef3e6bb3004859e3ee1f86797ac05bcb1b1980", "generation_seconds_batch": 24.75416525104083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6123769283294678, "target_z": 1.8515625161120617, "ce": 5.0178656578063965, "genuineness": 4.344170093536377, "identity": 0.660953164100647, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e1d6c26ef1383bd2c0f7a74150f4fdd11ce30a57851e64f1317613b73d48af13.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": "e203b161a2dcb5786f2811ebd41b36349a10cc144ab2b63f17899e0c8fa6c4dc", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a55a18bc03427e5ac8f56477b6f5419f2ad4fd37b4cfc7a22ddc06614696fdff", "generation_seconds_batch": 24.14434112107847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5478003025054932, "target_z": 1.7499999531285475, "ce": 5.895530700683594, "genuineness": 4.457139015197754, "identity": 0.5202731490135193, "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_Longing/e203b161a2dcb5786f2811ebd41b36349a10cc144ab2b63f17899e0c8fa6c4dc.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "e28f82480a45277e1cc1e08a66915b7a8c6ccd6e0fefc1e4e37b0cf1562a6a70", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e412f669eb3684a47bbc86d6ba0cd20fcd61f257e1ef53b1946d902175f48c68", "generation_seconds_batch": 25.341212878003716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.663597822189331, "target_z": 0.35937495605801334, "ce": 6.1894097328186035, "genuineness": 4.532451152801514, "identity": 0.5832599401473999, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e28f82480a45277e1cc1e08a66915b7a8c6ccd6e0fefc1e4e37b0cf1562a6a70.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "e2b66d7fa5f5e38ba2d3ee80e3679381ec7c8d96e95fc66ffba711e13458ee66", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "07ea49f17d66a061b5081a36b66b498c70bf652f0686b3e85210f1f109b8844d", "generation_seconds_batch": 23.342831077985466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4557419717311859, "target_z": 0.03247071424781537, "ce": 5.8875885009765625, "genuineness": 4.432034492492676, "identity": 0.6806735992431641, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e2b66d7fa5f5e38ba2d3ee80e3679381ec7c8d96e95fc66ffba711e13458ee66.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "e2f3f8ee6d06d5b1264224d7745a9555b5e21b7ec362466ba189045b4dd2b96c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "41f6fecbf951a40c1600445ec18d86c9ad817d8e9cbcdeb40a3d7f042eae4372", "generation_seconds_batch": 21.56126074597705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2177710384130478, "target_z": -0.34179687243671747, "ce": 6.0146708488464355, "genuineness": 4.457139015197754, "identity": 0.758493185043335, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e2f3f8ee6d06d5b1264224d7745a9555b5e21b7ec362466ba189045b4dd2b96c.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "e3246fa8e71f08489162a98f76eabadacf558ee3065653fdd1221c0ceda5a0b8", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "22ec18400ba1fd0e303548c381b5f1362c1546b7f4d7a8f9f117e38f6206309d", "generation_seconds_batch": 21.622182330000214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.979029655456543, "target_z": 0.85546878295649, "ce": 5.6334228515625, "genuineness": 4.68307638168335, "identity": 0.598080039024353, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e3246fa8e71f08489162a98f76eabadacf558ee3065653fdd1221c0ceda5a0b8.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "e34ef5104969c3244c8f522c86a800f60d300ad9983b0bcd142b7c54c8da509b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b697ea17320649cc80b4a36979c96eef4c210c409e524cc01c9f6600b465a3b9", "generation_seconds_batch": 26.27262021508068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9914482235908508, "target_z": 0.8750000234357262, "ce": 6.324435234069824, "genuineness": 4.268857479095459, "identity": 0.5802361369132996, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e34ef5104969c3244c8f522c86a800f60d300ad9983b0bcd142b7c54c8da509b.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "e35966e8303810741ccb95a1fd4ac4ae1a9217887de723120f6f92c1744aae76", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8d3fa062aee27002688abf3c3ede11c00c1ab39581768af23a52e4c291783786", "generation_seconds_batch": 26.813732582959346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.254721999168396, "target_z": 1.2890625278299248, "ce": 5.863759994506836, "genuineness": 4.545003414154053, "identity": 0.42042145133018494, "hypothesis": "The 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_Longing/e35966e8303810741ccb95a1fd4ac4ae1a9217887de723120f6f92c1744aae76.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "e48245bfa643547b9beb710ed1e38919b01d0713a3bf76de2f9e589c6411dcaf", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ef8cdb8a5d271c27aff20080ec9a81c300fc714ebc99c2ef61d13a391488b151", "generation_seconds_batch": 21.717292358982377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6735327243804932, "target_z": 0.3750000234357262, "ce": 6.022613525390625, "genuineness": 4.300237655639648, "identity": 0.49511122703552246, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e48245bfa643547b9beb710ed1e38919b01d0713a3bf76de2f9e589c6411dcaf.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "e484982f224248666ff8a879159326ed52e91bcea84125c6c37bfe8ee973601f", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "46beb2c6bda588b0b4f109437420e98cebbf47faf59a347f13c5458011c1d3a4", "generation_seconds_batch": 22.83506137493532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8160414695739746, "target_z": 2.171874897468698, "ce": 5.7247633934021, "genuineness": 4.607763767242432, "identity": 0.8372421860694885, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e484982f224248666ff8a879159326ed52e91bcea84125c6c37bfe8ee973601f.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "e48fe69b1e90d07a28ca7afbd514cec56cdf0528d0b4a4682666de5cfe0f809c", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ce43b9baa4a32b0150a357b6a93bc8f18d333d1a8c46be13e39b7dddd0cd2f7", "generation_seconds_batch": 23.478690747986548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9889644980430603, "target_z": 0.871093756591298, "ce": 5.359400749206543, "genuineness": 4.344170093536377, "identity": 0.6147598028182983, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e48fe69b1e90d07a28ca7afbd514cec56cdf0528d0b4a4682666de5cfe0f809c.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": "e4d4783914436be37f71d4a78c689109d7db8c74177591d28cb05a1f19f6a38a", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4959637e216ff54e48b38bb607be3c9a61f76cb580569f3d2244957c9b0bdbb1", "generation_seconds_batch": 21.917784277931787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9119693040847778, "target_z": 0.7499999531285476, "ce": 5.816103935241699, "genuineness": 4.482243061065674, "identity": 0.19836339354515076, "hypothesis": "De sleutels liggen op de keukentafel. Die keken in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e4d4783914436be37f71d4a78c689109d7db8c74177591d28cb05a1f19f6a38a.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "e52906742ad88565cd59a1b6de91a28500f1801bc1131ea639b588486c04e3b4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f64975d0eab1f7ae489985bbcbca604c89d587bc44c351e522d769dc62703595", "generation_seconds_batch": 16.32508714508731, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0063505172729492, "target_z": 0.8984375307593907, "ce": 5.673136234283447, "genuineness": 4.7332844734191895, "identity": 0.7929070591926575, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e52906742ad88565cd59a1b6de91a28500f1801bc1131ea639b588486c04e3b4.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "e58d2ca2b18d4a55fae439878e1b1292b0b1468c630e4e9855cf6eed2692f098", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a9e0e8a5469d248e64d5e822dda680a21199368a4c5951ebddcec15c08ed3176", "generation_seconds_batch": 25.125808184035122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09482714533805847, "target_z": -0.5351562609854966, "ce": 6.157639026641846, "genuineness": 4.356721878051758, "identity": 0.7142560482025146, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e58d2ca2b18d4a55fae439878e1b1292b0b1468c630e4e9855cf6eed2692f098.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "e5c0a3b60f62981c55cff83451280fee6bfde88d88e1decb61f132b7e4d10db3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3bf97bf7785ad141775f77ffc0f0fca9478240a134357daab220a4c0a9565518", "generation_seconds_batch": 18.837989312014543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4136797189712524, "target_z": 1.5390624809584725, "ce": 5.95112943649292, "genuineness": 4.7332844734191895, "identity": 0.5900592803955078, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e5c0a3b60f62981c55cff83451280fee6bfde88d88e1decb61f132b7e4d10db3.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "e601007392315fad3ce0647cbec8d0757695cdbb29e22dc960bd1d3c42e5d2a7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "10c309a2fbb555da78e2b908aa278e4d729c065b2d1671a42228c4727a50f595", "generation_seconds_batch": 21.263523216941394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7961719036102295, "target_z": 2.1406251376848915, "ce": 6.395919322967529, "genuineness": 4.532451152801514, "identity": 0.2907123267650604, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e601007392315fad3ce0647cbec8d0757695cdbb29e22dc960bd1d3c42e5d2a7.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "e63da059c81372ab4cd680d962005834602594e438424663254fd43d1b53a6a6", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "656f5ace1cc513601551791df872f24e3c981ae7ecbf5971fd7ab1d5702e7f09", "generation_seconds_batch": 26.299632289097644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4295077323913574, "target_z": -0.008789053528511061, "ce": 6.157639026641846, "genuineness": 4.356721878051758, "identity": 0.5521118640899658, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e63da059c81372ab4cd680d962005834602594e438424663254fd43d1b53a6a6.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "e672842fce38a7f84067a7bd88d923eb60fa81440165897be46a6a56bda2b756", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "05a36c08645c06dfb88fed42025e60a612adb6957faea71b904e803771a658ef", "generation_seconds_batch": 25.506421179976314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5853608250617981, "target_z": 0.23632811291595368, "ce": 6.23706579208374, "genuineness": 4.6705241203308105, "identity": 0.6904484033584595, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e672842fce38a7f84067a7bd88d923eb60fa81440165897be46a6a56bda2b756.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "754e30767b8d9d689b8af3644ebf265433dea11136b6dbbf5a7aabc1631eb807", "generation_seconds_batch": 17.765595064964145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3307800590991974, "target_z": -0.16406250439419867, "ce": 6.38003396987915, "genuineness": 4.356721878051758, "identity": 0.4751393795013428, "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_Longing/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "e70dfa4dc9ddf99245e4952b85118342d9e575652e89abd6b2623a70aba1dd2e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e8244238bb0a6607234212505358bd56238fc9db28d3c89710b8f0a1f2b85702", "generation_seconds_batch": 24.662895512068644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24385003745555878, "target_z": -0.3007812580560309, "ce": 5.990842819213867, "genuineness": 4.557555198669434, "identity": 0.12295973300933838, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e70dfa4dc9ddf99245e4952b85118342d9e575652e89abd6b2623a70aba1dd2e.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "e70f4161233f5b2aa4bdcde0f66ba8178a5a4ec50d33aac42400ca83eafd71a9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5580f2e48e5e108588199d7881a685c558670f01bd38149db7cd4e3328c3bc73", "generation_seconds_batch": 24.089473271975294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.736562728881836, "target_z": 2.0468751083902337, "ce": 5.681078910827637, "genuineness": 4.557555198669434, "identity": 0.40197840332984924, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e70f4161233f5b2aa4bdcde0f66ba8178a5a4ec50d33aac42400ca83eafd71a9.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "e72e93b92a35c2a3c91387eb00ef6f87764f4e44e6526e31a818ce00b380786e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c7568e2e8705b572920c1f80029bf0a9d9541c4cb16a7ac0efc1f406abf511c0", "generation_seconds_batch": 22.556187741924077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4881911277770996, "target_z": 1.65624992383389, "ce": 4.9156036376953125, "genuineness": 4.143336772918701, "identity": 0.5062042474746704, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e72e93b92a35c2a3c91387eb00ef6f87764f4e44e6526e31a818ce00b380786e.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": "e7b99a2ed5436a667dc6cd39ae20d1ee0e5adf7e545d1cfac039b619b5e006bb", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "726cbf0a8a0aff26a11553e7db723b4669f27322c04556fba1f2e1602cb72501", "generation_seconds_batch": 21.16335828602314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7318999767303467, "target_z": 0.46679682556526503, "ce": 5.442798614501953, "genuineness": 4.281409740447998, "identity": 0.5014306306838989, "hypothesis": "La carretera gira a la izquierda tras el puente. Sige hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e7b99a2ed5436a667dc6cd39ae20d1ee0e5adf7e545d1cfac039b619b5e006bb.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "e868da18b2e705f824cce141bf280d576eed40ecdfe4b70e2f7640d743698a9e", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "520b49d08bb8001b6bc461eaf357b431cc71cdd383bde6d5c96acb282920e679", "generation_seconds_batch": 18.7919943400193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09979459643363953, "target_z": -0.5273437272966403, "ce": 6.054384231567383, "genuineness": 4.494794845581055, "identity": 0.5396925210952759, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e868da18b2e705f824cce141bf280d576eed40ecdfe4b70e2f7640d743698a9e.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "e8909614f2162caedcc063d299181c7f0b57ee4689027739f598042070c44b29", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3e22214a79a8838ec354945ae626fc13e848ad38697a05904bd6d3dd74d82671", "generation_seconds_batch": 23.76023220794741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6223118305206299, "target_z": 1.8671875834897746, "ce": 6.181467056274414, "genuineness": 4.482243061065674, "identity": 0.4270837903022766, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e8909614f2162caedcc063d299181c7f0b57ee4689027739f598042070c44b29.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "e89252cf3f80352cb966d4adc66d9b1da9ade67d0b0ff0584f89740d4772bc91", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9869c5838d77ca78b9d3db9393bc2c1f60ba36fc35ce7f695f08a4a392fe8e56", "generation_seconds_batch": 25.341212878003716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31153127551078796, "target_z": -0.19433593182416006, "ce": 6.149696350097656, "genuineness": 4.796044826507568, "identity": 0.6947568655014038, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e89252cf3f80352cb966d4adc66d9b1da9ade67d0b0ff0584f89740d4772bc91.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "e8f4420d72a2fc0b0fd5ddb5a699119d0a6b9bcb17a309af4770cbc91b26306b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "00f843521a6e68e8e4071f08b57dba52dcfbad63cba6a977791aa9cfa3009a06", "generation_seconds_batch": 17.625033886055462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1255688667297363, "target_z": 1.0859375893487062, "ce": 6.221180438995361, "genuineness": 4.519899368286133, "identity": 0.6804938316345215, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e8f4420d72a2fc0b0fd5ddb5a699119d0a6b9bcb17a309af4770cbc91b26306b.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "e8f6ee3e419f51265e86930c8b7d22ef6e5f6d9d2c001fe3fa19da1df64d7632", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "154194f7789465300e77bb336d04a944a1bd28350e67e2437e76fc4d30d9afe6", "generation_seconds_batch": 21.647322205943055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6263421177864075, "target_z": 0.30078123462030465, "ce": 6.109982967376709, "genuineness": 4.093128204345703, "identity": 0.5084588527679443, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e8f6ee3e419f51265e86930c8b7d22ef6e5f6d9d2c001fe3fa19da1df64d7632.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "e90e6f13908c07b3a61a6b5e2c0d21a5ce1e66a983eea2966ca00abca2424c64", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e17f22b023cb2471b48d7afceb1f4cf5ece425cf5d38bbae140afa0983cae63f", "generation_seconds_batch": 26.06381359603256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7663671970367432, "target_z": 2.093749935551753, "ce": 5.079421520233154, "genuineness": 4.20609712600708, "identity": 0.3657301664352417, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e90e6f13908c07b3a61a6b5e2c0d21a5ce1e66a983eea2966ca00abca2424c64.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": "e91f6d51975822c575541a8bac6fc2de9639e9659c0cef2fcf69a38af1ef9dd1", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "622ca0985bae9b871245d5f2c26784e799d326a9b1cb2188912891e2ccdeb4f9", "generation_seconds_batch": 18.15546289109625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0510573387145996, "target_z": 0.9687499589874792, "ce": 5.967014789581299, "genuineness": 4.394378662109375, "identity": 0.3706784248352051, "hypothesis": "De sleutels liggen op de keukentafel. Keek in de la. En daarna, naast het raam, neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e91f6d51975822c575541a8bac6fc2de9639e9659c0cef2fcf69a38af1ef9dd1.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "e925b23342346a85cdef6480dc2eba627f5974c0b090cdbd71edb3ed7a57bd06", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9074a5daba44d29fd0c59eaae9d5bfa0fb1d976202f56ed454c2880ce0dea67d", "generation_seconds_batch": 26.400480692042038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8622950315475464, "target_z": 0.6718749912116027, "ce": 6.0146708488464355, "genuineness": 4.545003414154053, "identity": 0.5156601667404175, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e925b23342346a85cdef6480dc2eba627f5974c0b090cdbd71edb3ed7a57bd06.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "e9274972e735ef54ca1ec47f65e958e6da7c1da9b2de1ba8782a7e0c06ffda67", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a9f5ec7a1cd4615e418f213cdb2d90fcc9146489520911e20ff36f4b25846a6e", "generation_seconds_batch": 22.36954315705225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9849340915679932, "target_z": 2.437499917974958, "ce": 6.006728172302246, "genuineness": 4.570107460021973, "identity": 0.5344101190567017, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e9274972e735ef54ca1ec47f65e958e6da7c1da9b2de1ba8782a7e0c06ffda67.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "e966898ae12be4906b67369935e5877f029d1cd53e067dcd238d35534ff35ea2", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2ba5053af01d4ed20392e334181ae23045287f8cf4292d50c785d3b1793c8a0a", "generation_seconds_batch": 21.717247380060144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3888425827026367, "target_z": 1.5, "ce": 5.796247482299805, "genuineness": 4.68307638168335, "identity": 0.5982669591903687, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e966898ae12be4906b67369935e5877f029d1cd53e067dcd238d35534ff35ea2.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "e972ef9c58f27a7da046368be7887f1b205700833a40f6de6443a0413faca254", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a228697d87cb11e79f9b93200bcdebff1e53c7a00a1a66f3689fad45f3860ed1", "generation_seconds_batch": 17.640430091065355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9864807724952698, "target_z": 0.8671874897468698, "ce": 6.427689552307129, "genuineness": 4.595211505889893, "identity": 0.6663439273834229, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/e972ef9c58f27a7da046368be7887f1b205700833a40f6de6443a0413faca254.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": "e996250a44356e2de300aabb704e48ee642515696e55454cae8ad72cf3f24101", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2fdeafe79410b7b318b8b87e54dc972b61f1aa23496eb448d778b988abab1bf7", "generation_seconds_batch": 19.309784884913824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5841189622879028, "target_z": 0.23437497949373956, "ce": 5.95112943649292, "genuineness": 4.607763767242432, "identity": 0.7501416206359863, "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_Longing/e996250a44356e2de300aabb704e48ee642515696e55454cae8ad72cf3f24101.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "e46e492f50eb24d8d5c715e1d08e46a447554a5196f69d0dd6b51f55b1e31d78", "generation_seconds_batch": 16.633022353053093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3295381963253021, "target_z": -0.16601563781641276, "ce": 6.332377910614014, "genuineness": 4.362998008728027, "identity": 0.46357646584510803, "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_Longing/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "ea1c312bc9d55654ac52d8f9e6bd017dd0c4051eeb8afac1843ced9735f17802", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f41625a1bae06316674464a3fd6dafc98eaa643fc0a87d9ccb45af5f71c4408", "generation_seconds_batch": 24.662895512068644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14698517322540283, "target_z": -0.4531249853526711, "ce": 6.09409761428833, "genuineness": 4.2374773025512695, "identity": 0.617455244064331, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ea1c312bc9d55654ac52d8f9e6bd017dd0c4051eeb8afac1843ced9735f17802.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": "ea2d33eb2ad1a25b537f9a760de7af5457182ec4ef94bf6c2cc93609087dff09", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4a1ff8c75850009d65a2a41f5aa7cf43cf3a780af052b09d2419818175a652a", "generation_seconds_batch": 15.010896622086875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8995507955551147, "target_z": 0.7304688063922162, "ce": 5.395142555236816, "genuineness": 4.143336772918701, "identity": 0.31552040576934814, "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_Longing/ea2d33eb2ad1a25b537f9a760de7af5457182ec4ef94bf6c2cc93609087dff09.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "ea516395d41df8aa3cbad61dd2a279dfc12f1744e0c489b2a12571090dca0ea9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bf905a271c36af0969e0c76322d6e206785629edfb342d0bd982f08ddcfb68c0", "generation_seconds_batch": 25.146220876951702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0048038959503174, "target_z": 2.468750052730384, "ce": 6.054384231567383, "genuineness": 4.494794845581055, "identity": 0.40530216693878174, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ea516395d41df8aa3cbad61dd2a279dfc12f1744e0c489b2a12571090dca0ea9.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "ea724a949c3260bc243c8029909d6a8d6c77456a0d8dbf613c97c0fcc8a2ae1d", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "32e92e9e009ba78bc63f16ce4a3e12753cf2f40afd16da1d5e92c719a145279d", "generation_seconds_batch": 24.8236044900259, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5776050090789795, "target_z": 1.7968751552616862, "ce": 5.95112943649292, "genuineness": 4.645420074462891, "identity": 0.7546888589859009, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ea724a949c3260bc243c8029909d6a8d6c77456a0d8dbf613c97c0fcc8a2ae1d.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "eb324ecc3d9fbbd91a150eaef93e6b326fab50d7f10ddf183361d81af2541f25", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f8260e2644133e7d6cac50c08da79ee3100cda225124b22c9cac48fdf390ee53", "generation_seconds_batch": 22.877032682998106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4881911277770996, "target_z": 1.65624992383389, "ce": 5.669164657592773, "genuineness": 4.68307638168335, "identity": 0.5233966112136841, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/eb324ecc3d9fbbd91a150eaef93e6b326fab50d7f10ddf183361d81af2541f25.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "990b9a1a377cce959e63e4334f924d0c29e2765ccdb889ce726caa4dfdbe82f6", "generation_seconds_batch": 19.213704110006802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.263719767332077, "target_z": -0.2695312404792362, "ce": 6.205295085906982, "genuineness": 4.319066047668457, "identity": 0.7955559492111206, "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_Longing/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "ec09a618f14ee6252c0a7ee384b4854a1cf13a4ce86d4ac186eebec947af49fb", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "25b2d6b87e49986b430e0d9c5a374b289f0df38c3c9d0742c5bb9853a0cc4ea9", "generation_seconds_batch": 21.1760967860464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2199499607086182, "target_z": 1.2343749794937395, "ce": 5.879645347595215, "genuineness": 4.306513786315918, "identity": 0.807495653629303, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ec09a618f14ee6252c0a7ee384b4854a1cf13a4ce86d4ac186eebec947af49fb.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "ec40fa4c228930cbeae668fa1bdff26d3beda0cd1e68655007a1a3765e621b84", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "52b6a48719c888c57bd2cfaa395de8e3ec9984d7202c9466f53e0f046200d11b", "generation_seconds_batch": 26.299632289097644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22398032248020172, "target_z": -0.33203125219709934, "ce": 6.173524379730225, "genuineness": 4.149612903594971, "identity": 0.3167746663093567, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ec40fa4c228930cbeae668fa1bdff26d3beda0cd1e68655007a1a3765e621b84.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "ecacfb1692ba0d7c6bb26b8c947efea48a0efdf85f604cd62579ea510b8b950e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "39c93dbb0831c9edfb120e8b09da3ae779107285fad2ae7a3b93a9e9d0ad5c84", "generation_seconds_batch": 25.50411948899273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4037449359893799, "target_z": 1.5234376010665693, "ce": 6.117925643920898, "genuineness": 4.7332844734191895, "identity": 0.8238788843154907, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ecacfb1692ba0d7c6bb26b8c947efea48a0efdf85f604cd62579ea510b8b950e.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": "edbcc4180705af4536b327137fecd6a1b0a0d84b5e38a529a924b2b30ebd1123", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c81bd452f45364ad751b76cdf9f3a2b05153c0628d1c48e6be6c84f740c3fe92", "generation_seconds_batch": 16.42294567602221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4981260299682617, "target_z": 1.6718749912116027, "ce": 5.990842819213867, "genuineness": 4.457139015197754, "identity": 0.43137532472610474, "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_Longing/edbcc4180705af4536b327137fecd6a1b0a0d84b5e38a529a924b2b30ebd1123.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "edbd702ac6cb9390f05fb520e04970bf56dfe34ba4ebae594a0b00eb45ba4405", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "775ff3f930403fd7dda91ab27d2f1235b97da1b7e987c4737fbe00891ab204f9", "generation_seconds_batch": 24.936994355986826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9849340915679932, "target_z": 2.437499917974958, "ce": 6.0305562019348145, "genuineness": 4.413206577301025, "identity": 0.43393784761428833, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/edbd702ac6cb9390f05fb520e04970bf56dfe34ba4ebae594a0b00eb45ba4405.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "ee150f042ebe4572e7b59e36071350ef865ba77936842b0dae8a74e80c0e9fdb", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0dfa51b02dca4f0e21edb5caaba4157098e757c778be5445d6e5c53cd44d9b10", "generation_seconds_batch": 22.870538763003424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6769535541534424, "target_z": 1.9531250790955759, "ce": 6.2767791748046875, "genuineness": 4.507347106933594, "identity": 0.31427058577537537, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ee150f042ebe4572e7b59e36071350ef865ba77936842b0dae8a74e80c0e9fdb.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "eec107b1164f5bca31a2cbfc658cf2f75b9b756825a3e35872889b4188db4306", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "558e6d71ee1b813c5ef0f827f72326857c80884ee782421d5500daf035495820", "generation_seconds_batch": 23.53832638298627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4881911277770996, "target_z": 1.65624992383389, "ce": 6.022613525390625, "genuineness": 4.457139015197754, "identity": 0.5695327520370483, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/eec107b1164f5bca31a2cbfc658cf2f75b9b756825a3e35872889b4188db4306.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "ef3da845d6469be15e40d513c55c685f406964e6ca64e6e4d92a7fdff05a9cc8", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e455148e1525656cefb6dfa905785c7a6083be757442be164c639e910f523947", "generation_seconds_batch": 23.11361532798037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7169977426528931, "target_z": 0.4433594119845054, "ce": 5.903473377227783, "genuineness": 4.400654315948486, "identity": 0.5560370683670044, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ef3da845d6469be15e40d513c55c685f406964e6ca64e6e4d92a7fdff05a9cc8.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "ef54d4fa9743ab29493031f671b0413533e6b4880c80e9e74aeb4b0027de7208", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "998d0b5230e7cf773aa531648bbdff2805ed1bf2fbbb6517771e49c1049900c2", "generation_seconds_batch": 19.16498312400654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4850808382034302, "target_z": 0.07861326870822465, "ce": 6.149696350097656, "genuineness": 4.557555198669434, "identity": 0.5260457992553711, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ef54d4fa9743ab29493031f671b0413533e6b4880c80e9e74aeb4b0027de7208.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "ef790e939a45318aee4abde99d55c373b843db93d9c2d6b59dcfbf7f08336526", "bucket": "emo_Longing", "phase": "wording", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "608cc04a182c64a24b92d5374b5ab5c618018a45f1e0dd6275801bc9b4bb792d", "generation_seconds_batch": 20.680847611976787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3491032123565674, "target_z": 1.437500105460768, "ce": 5.871703147888184, "genuineness": 4.796044826507568, "identity": 0.8065950870513916, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ef790e939a45318aee4abde99d55c373b843db93d9c2d6b59dcfbf7f08336526.mp3" }, { "id": "emo_Longing-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Longing-en-0", "key": "efadc1db3375a0c2eecc9304fbc4d2f4b5742bef3df2f6ab661a893ea9aa47b1", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The door is still open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] I put your coat on the chair.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1408a00a1b5a956d9fea96f1fdb32901305315b1ec3e6134835ec3304498f0c4", "generation_seconds_batch": 16.879675847943872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0013830661773682, "target_z": 0.8906249970705342, "ce": 6.197352409362793, "genuineness": 4.381826400756836, "identity": 0.3766833543777466, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/efadc1db3375a0c2eecc9304fbc4d2f4b5742bef3df2f6ab661a893ea9aa47b1.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "f0f6a88957ab0ed7ba63afbb6311b6294ffa2eabf9a94df839ef865c4983e224", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "96004523071a7a42d337170978222328a6cca0504e15434c448c7b6e64ab9fe6", "generation_seconds_batch": 17.792354698991403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5875396728515625, "target_z": 1.8124998476677796, "ce": 6.348263263702393, "genuineness": 4.645420074462891, "identity": 0.539376974105835, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f0f6a88957ab0ed7ba63afbb6311b6294ffa2eabf9a94df839ef865c4983e224.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "f0f752a82255625e7ea7dcbc4235f1d66e9d7aa83efca55929c4e67c1a8703ca", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d180311ee21eee68d67507594924b03514efb3f8e8be0d3dd5fa125363b99d0", "generation_seconds_batch": 25.105259974021465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1047620177268982, "target_z": -0.5195312404792363, "ce": 6.117925643920898, "genuineness": 4.595211505889893, "identity": 0.40100646018981934, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f0f752a82255625e7ea7dcbc4235f1d66e9d7aa83efca55929c4e67c1a8703ca.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": "f1620d91bd78dcd2df53bdd2d0cf291e2cbf8883be79b6253ce847474e2f4375", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "472b3a39bd4cd348ba02d97c216b5b21a20929c8bbb123d0ffcfa0fe6335b5b1", "generation_seconds_batch": 19.676516829058528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0138015747070312, "target_z": 0.9101561438068656, "ce": 5.577824115753174, "genuineness": 4.419482707977295, "identity": 0.7086523771286011, "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_Longing/f1620d91bd78dcd2df53bdd2d0cf291e2cbf8883be79b6253ce847474e2f4375.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "f1e289fd5b305a8dc02c049673ee92b1f99e7f33c939b483c23bb2c14dd2db5a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6361ff842d7fa5419467482e7afd7a266d85ff42a2ac505082a8d7619cf3b14a", "generation_seconds_batch": 22.59443043509964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007897138595581055, "target_z": -0.6718749912116027, "ce": 6.1894097328186035, "genuineness": 4.557555198669434, "identity": 0.5247955322265625, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f1e289fd5b305a8dc02c049673ee92b1f99e7f33c939b483c23bb2c14dd2db5a.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "f1f8af03f78e5b487a32beba9bd2c7b288e153b15d825f1e87a99080acb3b077", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6aa2dea8f12fd0e0d594f3ce103e4c32657acb3e468e6f7e4688155af9effeb6", "generation_seconds_batch": 25.1199758190196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0907968282699585, "target_z": 1.031250041012521, "ce": 5.911416053771973, "genuineness": 4.645420074462891, "identity": 0.8295043706893921, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f1f8af03f78e5b487a32beba9bd2c7b288e153b15d825f1e87a99080acb3b077.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "f2105f2eaead08cabedcb4fcf0ca872df782cfcb5f71bf5c02ecc4a7d053b76e", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a2c3967042132fd2e0d32627b4790281765c8e9e91ed57590dfbaa58835c3b69", "generation_seconds_batch": 21.977943881996907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9948689937591553, "target_z": 2.4531249853526713, "ce": 6.165581703186035, "genuineness": 4.65797233581543, "identity": 0.4292270541191101, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f2105f2eaead08cabedcb4fcf0ca872df782cfcb5f71bf5c02ecc4a7d053b76e.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "a71741bc3783ec8622eea2acb624196a719a21caa3c6a891e93878ad9e2e6ac8", "generation_seconds_batch": 16.446668064105324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.869746208190918, "target_z": 0.6835937917448873, "ce": 6.324435234069824, "genuineness": 4.507347106933594, "identity": 0.5537787675857544, "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_Longing/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Longing-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Longing-fr-0", "key": "f2bce4fcc3b5f19ad1fca844363a83a476b1fd36bf29fac931de76101862a16a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b329d502902449936f23d7abb16acdab5d4b71fd38193af5e59ba04b6be3ab64", "generation_seconds_batch": 21.78088195307646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0560247898101807, "target_z": 0.9765624926763355, "ce": 6.268836498260498, "genuineness": 4.68307638168335, "identity": 0.6107528805732727, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f2bce4fcc3b5f19ad1fca844363a83a476b1fd36bf29fac931de76101862a16a.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "f2ff1cac9fe0cccda4024d9eaa267fa875c1652d85c7cbcab4188c578871ee94", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "325bf4a30a939b4bdb020ba3032f4bf469ad54d719b688a7f621c59cdf809cae", "generation_seconds_batch": 26.762310898979194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23018960654735565, "target_z": -0.3222656319574812, "ce": 6.213237762451172, "genuineness": 4.6203155517578125, "identity": 0.7179347276687622, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f2ff1cac9fe0cccda4024d9eaa267fa875c1652d85c7cbcab4188c578871ee94.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": "f3209f32f00aa217ec3d16ec11e2aeb852a5febd6d6fb3d98fa3ecf15ec4d48a", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "970a5f3583f7efdb4495185021170279fe0534619e9827b80d9db86a33b754af", "generation_seconds_batch": 18.51978092396166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9153900146484375, "target_z": 2.3281248213025876, "ce": 5.6413655281066895, "genuineness": 4.758388519287109, "identity": 0.7993391156196594, "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_Longing/f3209f32f00aa217ec3d16ec11e2aeb852a5febd6d6fb3d98fa3ecf15ec4d48a.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "f41347be37a2672489f7593ec5390ac155a349a18922b062dfae6d7dc37fc399", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "22ac3b1d29c43f093018545945e61da36a9a4a1a0ab7e0641af19e6a93deb4b7", "generation_seconds_batch": 17.781038894085214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.09576416015625, "target_z": 1.0390623872155675, "ce": 5.796247482299805, "genuineness": 4.720732688903809, "identity": 0.14302802085876465, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f41347be37a2672489f7593ec5390ac155a349a18922b062dfae6d7dc37fc399.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "f4c764420187f2f2961ddb6deac0146f3832dd997e1852d5a5a619f78c398221", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "30cea9dc5b0640dd0cd4483fbf4f839b060bf0e11ea273751ab66db0a97d898b", "generation_seconds_batch": 21.654154394054785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1991431713104248, "target_z": -0.371093756591298, "ce": 5.911416053771973, "genuineness": 4.457139015197754, "identity": 0.5244570374488831, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f4c764420187f2f2961ddb6deac0146f3832dd997e1852d5a5a619f78c398221.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "f4fa0314bb714d97d34dd5bab5afd588bff10fd77ce3942ee7cab8380451a5d6", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3c9b64a8f75864651bdf19691f415b3afd1d86a3d8e3cd3f32517890cc48038d", "generation_seconds_batch": 22.648169490974396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0246734619140625, "target_z": 2.4999998125141905, "ce": 5.732706069946289, "genuineness": 4.595211505889893, "identity": 0.8613053560256958, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f4fa0314bb714d97d34dd5bab5afd588bff10fd77ce3942ee7cab8380451a5d6.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "f5090de760293f120fd41a40bb02003ff543a54d42076d546dcd7b8211199cfb", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0fe210aa700437c1465b729092a5f1b3335f877c3de55989cb58acc4a0040220", "generation_seconds_batch": 22.509251386974938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4385168552398682, "target_z": 1.5781249619169448, "ce": 5.7684478759765625, "genuineness": 4.532451152801514, "identity": 0.5990315079689026, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f5090de760293f120fd41a40bb02003ff543a54d42076d546dcd7b8211199cfb.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "f5483881954e6b3f7197185a208d5a1d5625949afc6adc5b9366c976297ceabb", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c5afe8b43cfbd155ec198ae72b0a2da7786d336c8d06b0c3d70e8a6f245337c6", "generation_seconds_batch": 27.051700858050026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16809675097465515, "target_z": -0.41992185778938856, "ce": 6.23706579208374, "genuineness": 4.444586753845215, "identity": 0.7280598282814026, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f5483881954e6b3f7197185a208d5a1d5625949afc6adc5b9366c976297ceabb.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "f5dd82b7f880f8698bcf5450474c05cc4c7888bd5fe23077ce2950fd0d45a9db", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7afaa72217a8b153ebbcfa453c5ab2305fef6a88ca864d27b566fa13fa78038a", "generation_seconds_batch": 21.951000688015483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5810143351554871, "target_z": 0.22949219280965671, "ce": 5.744620323181152, "genuineness": 4.494794845581055, "identity": 0.6674787998199463, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f5dd82b7f880f8698bcf5450474c05cc4c7888bd5fe23077ce2950fd0d45a9db.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "f690a848564ceeadca11fdc4f213605dd215f4ddeca08f7d9f76c04fedc7765a", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d92ea146d71da785e906607413f546ad539112d85272266263d0c4d4e649b185", "generation_seconds_batch": 18.758378549013287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9451947212219238, "target_z": 2.3750000234357262, "ce": 6.157639026641846, "genuineness": 4.394378662109375, "identity": 0.4806936979293823, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f690a848564ceeadca11fdc4f213605dd215f4ddeca08f7d9f76c04fedc7765a.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "f6b3c172fb497d02f744e837b638755dbdf292f88943cb1021862ee6dbedd17b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1e99533692c37be7e2e27c194a471356fefed7e5b7efb99a6ca60f7d38bbc26c", "generation_seconds_batch": 25.22005522705149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6868884563446045, "target_z": 1.9687501464732888, "ce": 6.316492557525635, "genuineness": 4.494794845581055, "identity": 0.697226881980896, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f6b3c172fb497d02f744e837b638755dbdf292f88943cb1021862ee6dbedd17b.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "f72d1e8d503b861778b9d8a4452c768e43abc899dec2a5304b1855752ea687dc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cd97242752fe05f3cb3c430cff83069299abc5a0dabc718235d91a4d79dcb5eb", "generation_seconds_batch": 25.083324313978665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5207842588424683, "target_z": 0.13476564367534433, "ce": 6.3641486167907715, "genuineness": 4.137060642242432, "identity": 0.6762739419937134, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster, wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f72d1e8d503b861778b9d8a4452c768e43abc899dec2a5304b1855752ea687dc.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "1d2eebc13ae6d0a8a579732ea030fd0366118ed100da59cbf5bfd19833854676", "generation_seconds_batch": 22.19087321299594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3239498436450958, "target_z": -0.17480469134492382, "ce": 6.173524379730225, "genuineness": 4.469690799713135, "identity": 0.7642002105712891, "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_Longing/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.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": "f817d694fd7d0238bf966620854d9b72e54560b25f9a13d4db62bad87d53e8c1", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "baf66a9176a4577f26bb7bf000e31e5f94d35a2f05c7ba3172c42b197826cb58", "generation_seconds_batch": 16.619256684090942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6918559074401855, "target_z": 1.9765626801621452, "ce": 5.855817794799805, "genuineness": 4.093128204345703, "identity": 0.5000295042991638, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f817d694fd7d0238bf966620854d9b72e54560b25f9a13d4db62bad87d53e8c1.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "f840ce85d1b524fa6f02c3aaab2428fbbdbb008e73cdb3b5afd10c80b3556534", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c8f71b9465db947864474a388fe72f90e38274a8b7169e3fca456f9ff19e2819", "generation_seconds_batch": 26.06381359603256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4782562255859375, "target_z": 1.640624856456177, "ce": 4.969216823577881, "genuineness": 4.268857479095459, "identity": 0.3162209391593933, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f840ce85d1b524fa6f02c3aaab2428fbbdbb008e73cdb3b5afd10c80b3556534.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_Longing", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": "c7e1651d5d005c66429c532d1fee25c4f493595a5cbd800f39b3252f52437e21", "generation_seconds_batch": 16.57668074395042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27365463972091675, "target_z": -0.2539062199729758, "ce": 6.141753673553467, "genuineness": 4.293961524963379, "identity": 0.5355079174041748, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zum kleinen Holstor. Ich warte auf der anderen Seite.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "f89c4e272851448571c4e30ddab51f91fcf35ad25a19f55961cb8206435c88c0", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8572a448b5df8ec0c6627cf58b3706c3df16e259beb008ee4c0df52006835ca7", "generation_seconds_batch": 16.421415170072578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8920996189117432, "target_z": 0.7187500058589316, "ce": 5.736677646636963, "genuineness": 4.074300289154053, "identity": 0.41145890951156616, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/f89c4e272851448571c4e30ddab51f91fcf35ad25a19f55961cb8206435c88c0.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "f9978b050689ad51f10472ebf80d6a56172cb649ecbcf694ef3795998b2bf410", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "00374a836aa34f78fdf106094216561a973347c29b8ecba058e245285ffd62a0", "generation_seconds_batch": 22.28079798608087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.965064525604248, "target_z": 2.4062501581911517, "ce": 5.609594821929932, "genuineness": 4.582659721374512, "identity": 0.7500906586647034, "hypothesis": "J'ai trouvé la 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_Longing/f9978b050689ad51f10472ebf80d6a56172cb649ecbcf694ef3795998b2bf410.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "fa01507b44ed7c03e16408419cafdf721eae483553258125c352fb6cd5fc0eb9", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "eab5348b69b524ac51a3824617908af9f508e324319c75536785dfce445f86fa", "generation_seconds_batch": 25.123406919068657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1206014156341553, "target_z": 1.0781250556598498, "ce": 5.982900142669678, "genuineness": 4.532451152801514, "identity": 0.5934702157974243, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fa01507b44ed7c03e16408419cafdf721eae483553258125c352fb6cd5fc0eb9.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "fb976c02ff7fe8ef4a6265ae8479101de44d3a2a976ddb70a83ead1627662543", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f897829f1306fc7fc4dfd2e57b306c7292f6c01967ec4816c2d8338379ddd002", "generation_seconds_batch": 24.913294658996165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7852998971939087, "target_z": 0.5507812814917571, "ce": 5.990842819213867, "genuineness": 4.482243061065674, "identity": 0.7441637516021729, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fb976c02ff7fe8ef4a6265ae8479101de44d3a2a976ddb70a83ead1627662543.mp3" }, { "id": "emo_Longing-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Longing-fr-1", "key": "fbb29805a97bed7199dad68cb476b3cd74e2fed44250783282081bb0c4c6c049", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68319f277d1266d4a7df2615419cdb841d3e96582ac1c3e979f32058c226deb5", "generation_seconds_batch": 24.21085099002812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4320027828216553, "target_z": 3.140624950199082, "ce": 5.645336627960205, "genuineness": 4.645420074462891, "identity": 0.7460853457450867, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fbb29805a97bed7199dad68cb476b3cd74e2fed44250783282081bb0c4c6c049.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "fbeffbf32f67a7d6a81e0f434ab62a6b363786bf3142b5459e980fa9fe62b401", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "840d6b95155a82b9125aecc65d7e2470db6ec5f05925b20be2b33269d19f1707", "generation_seconds_batch": 23.029096418991685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4981260299682617, "target_z": 1.6718749912116027, "ce": 5.107220649719238, "genuineness": 4.319066047668457, "identity": 0.42522481083869934, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fbeffbf32f67a7d6a81e0f434ab62a6b363786bf3142b5459e980fa9fe62b401.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "fd530ed04630a4754f38b0bcd547b6a9cfe786876e1ea703c7eb3dc16d6b18e8", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ecc9a729960c3d0aded3178d9ecc82c3b236f0749a4ae0e7e9e07ab08de2cae9", "generation_seconds_batch": 17.03945005009882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9864807724952698, "target_z": 0.8671874897468698, "ce": 6.284721851348877, "genuineness": 4.419482707977295, "identity": 0.6778692007064819, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fd530ed04630a4754f38b0bcd547b6a9cfe786876e1ea703c7eb3dc16d6b18e8.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "fd74117838ac963f16adc5a7bdec139fef53485733f593fd709554e3bcd16196", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "26096e25a781a932117ce7deaa099ef300da31651c43c6137a1a2f33a8207dc6", "generation_seconds_batch": 18.367653392022476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8324904441833496, "target_z": 0.6249999765642738, "ce": 6.419747352600098, "genuineness": 4.18726921081543, "identity": 0.639795184135437, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fd74117838ac963f16adc5a7bdec139fef53485733f593fd709554e3bcd16196.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": "fd79231a2f94c4ebba5f5ca07980b6f6aea1b269d1cbb740f1460a9ba39c0ff0", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b6af5ab9669a3435f4546cf61a606818db7c90abb62e40ac33d652b1f8be7eaa", "generation_seconds_batch": 21.128862797049806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.319298505783081, "target_z": 1.3906249033276294, "ce": 5.645336627960205, "genuineness": 4.494794845581055, "identity": 0.6155411601066589, "hypothesis": "Escribí el número en el sobre, lélelo 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_Longing/fd79231a2f94c4ebba5f5ca07980b6f6aea1b269d1cbb740f1460a9ba39c0ff0.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": "fd81001d8afb8934dcbb2bcddda9f8b8f41284436fa0df781434bdfd9bd6f47b", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f5fb943d5b4dab34f4c4a22c9a9c5ae3001af78218fa44ae044966d08d5800da", "generation_seconds_batch": 25.27100669394713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9666110873222351, "target_z": 0.8359375424772537, "ce": 5.927301406860352, "genuineness": 4.482243061065674, "identity": 0.388558566570282, "hypothesis": "Someone moved the little blue chair. Uh it used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fd81001d8afb8934dcbb2bcddda9f8b8f41284436fa0df781434bdfd9bd6f47b.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "fd8a3dc9cfe4182485c9e9f730c5ebd179938775bed6f927268d65cc041dcbc4", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "376885e18323ab7410f40f3434aa82ee33c063f707bee15ad7ed8c75f9382643", "generation_seconds_batch": 23.11505231098272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0560247898101807, "target_z": 0.9765624926763355, "ce": 5.7247633934021, "genuineness": 4.344170093536377, "identity": 0.5036866664886475, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fd8a3dc9cfe4182485c9e9f730c5ebd179938775bed6f927268d65cc041dcbc4.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "fda6d0e589292e33adf5463c254c6ff302eaf089978d6af206127d87ae49ab72", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6297abd43d4b63bdbc9b9809265f1ed037037b8d02d9becab04ed6aef9606fca", "generation_seconds_batch": 22.43135752598755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.408712387084961, "target_z": 1.5312501347554257, "ce": 5.677107334136963, "genuineness": 4.482243061065674, "identity": 0.5172674059867859, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fda6d0e589292e33adf5463c254c6ff302eaf089978d6af206127d87ae49ab72.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "fda80edd4a22b431be562851348a4d0ab60ef7ac1c07f3cd5732938423e7a9f5", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eaff071b7682084ae1d7d810313411dd0525d4c01ca5f06545cf962e30c3628f", "generation_seconds_batch": 19.884153173072264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0907968282699585, "target_z": 1.031250041012521, "ce": 5.752562999725342, "genuineness": 4.545003414154053, "identity": 0.5322833061218262, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fda80edd4a22b431be562851348a4d0ab60ef7ac1c07f3cd5732938423e7a9f5.mp3" }, { "id": "emo_Longing-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Longing-es-1", "key": "fdbcecc01ba1bb5a3f4e05824bd8fcf0466cd04df1a9af4190d6aaff1eaef0ec", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ffce8580d5e1ae40358f4d0cef0916f1528e6ad067c48bc1e4b8e1ca46b1acb6", "generation_seconds_batch": 23.27804314706009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5478003025054932, "target_z": 1.7499999531285475, "ce": 5.760505676269531, "genuineness": 4.482243061065674, "identity": 0.5879614353179932, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fdbcecc01ba1bb5a3f4e05824bd8fcf0466cd04df1a9af4190d6aaff1eaef0ec.mp3" }, { "id": "emo_Longing-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Longing-nl-1", "key": "fddebd6f65c9bdc626e745d464d27b9b4d39d1a14d0806f67dd4c911efb334d7", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Het stond naast het oude raam.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "02cfe0d7201c42d3b8c25c812770c54581f779249775c737d6add2cb930308b8", "generation_seconds_batch": 21.89516553701833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8796810507774353, "target_z": 0.6992187653796953, "ce": 5.788304805755615, "genuineness": 4.507347106933594, "identity": 0.45823580026626587, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fddebd6f65c9bdc626e745d464d27b9b4d39d1a14d0806f67dd4c911efb334d7.mp3" }, { "id": "emo_Longing-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Longing-en-1", "key": "fde016b7fccd6ef746a542a2862bc3199c9dbc376a94c5721c729cf8e29a71a3", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] I found the little box.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] It was beside the old window.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7b544267d1a07d9549308840e5e5a21338459f8f7ce8fcd21c5b5c2b33f77815", "generation_seconds_batch": 24.52983590599615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9451947212219238, "target_z": 2.3750000234357262, "ce": 6.316492557525635, "genuineness": 4.557555198669434, "identity": 0.3442741334438324, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fde016b7fccd6ef746a542a2862bc3199c9dbc376a94c5721c729cf8e29a71a3.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": "febb9599c541f468f6fc41fc3d452946acd902c14ecebef86268106d8dcf606e", "bucket": "emo_Longing", "phase": "heldout", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ffe05420acbd813347a4430ae25806b39e0c2bd72f77676d8cfc9bc7f71c5425", "generation_seconds_batch": 22.001615589950234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40156593918800354, "target_z": -0.052734368042518784, "ce": 5.053607940673828, "genuineness": 4.532451152801514, "identity": 0.6982473134994507, "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_Longing/febb9599c541f468f6fc41fc3d452946acd902c14ecebef86268106d8dcf606e.mp3" }, { "id": "emo_Longing-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Longing-nl-0", "key": "fed732f029f4c5e3263088f7676647ed392c06b6b10aa6bd442270a20c98e90b", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] De deur staat nog open.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a559ca239fa01aa3b8bbdc6f62c0dcd33f7b5983a96456b87c9298343a83dc83", "generation_seconds_batch": 25.096704630064778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04018542170524597, "target_z": -0.621093756591298, "ce": 5.855817794799805, "genuineness": 4.256305694580078, "identity": 0.5778515338897705, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/fed732f029f4c5e3263088f7676647ed392c06b6b10aa6bd442270a20c98e90b.mp3" }, { "id": "emo_Longing-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Longing-de-1", "key": "ff147a6e753579f3cefa7a160dc51955e0ef30e429c5afbdde799f0932f93944", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e7d1d1e037960cde3922c00c4e4b236c39d120a1f65e4c7238b8ccb2c60fb27", "generation_seconds_batch": 25.220996520016342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4217461049556732, "target_z": -0.020996113981623016, "ce": 6.38003396987915, "genuineness": 4.507347106933594, "identity": 0.5850417613983154, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ff147a6e753579f3cefa7a160dc51955e0ef30e429c5afbdde799f0932f93944.mp3" }, { "id": "emo_Longing-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Longing-es-0", "key": "ffc285e9e682d0ce27efab2a807d40560cb265effcd66db3d95f4503b7d02171", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6f89703a39a8325facb3fae301aea191af0ae669467a3a5283e74b697c42b2b3", "generation_seconds_batch": 24.6354158410104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4276449382305145, "target_z": -0.01171875366183222, "ce": 6.062326908111572, "genuineness": 4.394378662109375, "identity": 0.3701486885547638, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ffc285e9e682d0ce27efab2a807d40560cb265effcd66db3d95f4503b7d02171.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "ffcab338755d056b2cca09528cc2cd00699551040017031c13a2c5c6e7ef48bc", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "48f3d2cf1acee21f5e0b2d8fcbffad96f33f1226a23b9f40fc39964a8fc50cfc", "generation_seconds_batch": 21.484699035063386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39256247878074646, "target_z": -0.06689451504639242, "ce": 5.935244083404541, "genuineness": 4.6956281661987305, "identity": 0.29419952630996704, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ffcab338755d056b2cca09528cc2cd00699551040017031c13a2c5c6e7ef48bc.mp3" }, { "id": "emo_Longing-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Longing-de-0", "key": "ffe8bf8cdad758b24d4ff7e2d7f7db439334d0d15acc853dd085d023ffc38007", "bucket": "emo_Longing", "phase": "grid", "candidate": "manual-bd19fff54e5e", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on vocal placement; project the ache from a high, fragile place in the throat, not from the chest.\nSCRIPT:\n(Begin with a slightly higher register, almost a fragile whisper carrying significant emotional weight.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the vowels to stretch and thin, suggesting the yearning is delicate and easily broken.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Maintain a shimmering, high-frequency texture that fades gently into the silence following the utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5bfb342785f68d94bcda982c3e3ef869c8a380d79710a28abfe8057768ddbaf6", "generation_seconds_batch": 32.261567434994504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5027773380279541, "target_z": 0.10644534966759703, "ce": 6.221180438995361, "genuineness": 4.645420074462891, "identity": 0.5444896221160889, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Longing/ffe8bf8cdad758b24d4ff7e2d7f7db439334d0d15acc853dd085d023ffc38007.mp3" }, { "key": "original-emo_Longing-de-0-seed1701-scale0.0", "bucket": "emo_Longing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "09fc382e55d0fa9addb71467f4e6b7867bc2a3e0748b0ff5e5a897bf7d0c8d60", "task_id": "emo_Longing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.04018542170524597, "target_z": -0.621093756591298, "ce": 6.109982967376709, "genuineness": 4.381826400756836, "identity": 0.43779242038726807, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/7d3ef096792c4becd5d0892f.mp3" }, { "key": "original-emo_Longing-de-0-seed1701-scale0.5", "bucket": "emo_Longing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "0e0d70ef5182f65a5bf7c656ae522f5c2e5a5ed68378c2328477fe2ddf49e1ac", "task_id": "emo_Longing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.015348285436630249, "target_z": -0.6601562375497705, "ce": 6.324435234069824, "genuineness": 4.607763767242432, "identity": 0.608555793762207, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/a0c1cd5d4875599f9408d18c.mp3" }, { "key": "original-emo_Longing-de-0-seed1701-scale0.75", "bucket": "emo_Longing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "f1281903835b3f2966f338d57f6eb614353f48fdc1f122415e89546aeb87c63c", "task_id": "emo_Longing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": -0.011972576379776001, "target_z": -0.7031249853526711, "ce": 6.205295085906982, "genuineness": 4.419482707977295, "identity": 0.37880420684814453, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/ec135dd97d6759bc93a0f3e4.mp3" }, { "key": "original-emo_Longing-de-0-seed1701-scale1.0", "bucket": "emo_Longing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "22cf3b6b60c356889c05073b2ab6a844f4adc05aeb8961ddabfe8d3e00f44816", "task_id": "emo_Longing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.2649616003036499, "target_z": -0.26757815392847456, "ce": 6.2767791748046875, "genuineness": 4.482243061065674, "identity": 0.4928191304206848, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/ea750519e3bd64f442b55054.mp3" }, { "key": "original-emo_Longing-de-0-seed1702-scale0.0", "bucket": "emo_Longing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "fd4c4ac686209e54d2f0799a94fc56ebba9d81fa5debda3ebb9e66a4f7d64845", "task_id": "emo_Longing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.05260398983955383, "target_z": -0.6015625161120618, "ce": 6.197352409362793, "genuineness": 4.68307638168335, "identity": 0.6049692034721375, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/61bd9e8d67d048332e98e174.mp3" }, { "key": "original-emo_Longing-de-0-seed1702-scale0.5", "bucket": "emo_Longing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "fc1916d8e8b1bcefc4eb38b6fa59be6decab7e849e793528ce0e35b6a107f772", "task_id": "emo_Longing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.12338986992835999, "target_z": -0.49023437976038187, "ce": 6.125868320465088, "genuineness": 4.532451152801514, "identity": 0.5036709308624268, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/a5b5bca7403b0f980e078ed5.mp3" }, { "key": "original-emo_Longing-de-0-seed1702-scale0.75", "bucket": "emo_Longing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "73256f8feddda466f06c33d607c8bfa24926cf4f727d4f2f4d1d02928fc858f6", "task_id": "emo_Longing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.05508771538734436, "target_z": -0.5976562492676336, "ce": 6.197352409362793, "genuineness": 4.507347106933594, "identity": 0.4983147978782654, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/b933207332d6fd9fad72de21.mp3" }, { "key": "original-emo_Longing-de-0-seed1702-scale1.0", "bucket": "emo_Longing", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "c3d2b466a60cb41a9f1268b7198c867aa5695341bb5272a0a2f08cc9a072c2b9", "task_id": "emo_Longing-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.03770172595977783, "target_z": -0.6249999765642738, "ce": 6.181467056274414, "genuineness": 4.444586753845215, "identity": 0.5753520131111145, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/889c28dfec72a9f20c497b35.mp3" }, { "key": "original-emo_Longing-de-1-seed1701-scale0.0", "bucket": "emo_Longing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "1879e2378fead889a40433d3ffbcc1821ed7a1e28cfab35b5d3b40402d321956", "task_id": "emo_Longing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42469552159309387, "target_z": -0.016357433821727618, "ce": 6.41180419921875, "genuineness": 4.268857479095459, "identity": 0.6078684329986572, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/d0195f2aa9efcf1c7fbb5711.mp3" }, { "key": "original-emo_Longing-de-1-seed1701-scale0.5", "bucket": "emo_Longing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "f8ec9b3c5b55675668581accfc58aed671b72d34b8b10630ca240161af73a5b2", "task_id": "emo_Longing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3823171555995941, "target_z": -0.08300779547248018, "ce": 6.3641486167907715, "genuineness": 4.545003414154053, "identity": 0.4978524446487427, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/6d8b4663e1fc7531b70a6c92.mp3" }, { "key": "original-emo_Longing-de-1-seed1701-scale0.75", "bucket": "emo_Longing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "e57aeceb19d2249727a178318c3cf064c513004f266f46df081201b7216cec01", "task_id": "emo_Longing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31898242235183716, "target_z": -0.18261717816232784, "ce": 6.268836498260498, "genuineness": 4.375550270080566, "identity": 0.4478684067726135, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/60f90bda0f7a22e01d0846f7.mp3" }, { "key": "original-emo_Longing-de-1-seed1701-scale1.0", "bucket": "emo_Longing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "1269907512f9d383d704ffefbce037375a7de7b5bb0cd90d52430880a87d4547", "task_id": "emo_Longing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4087066054344177, "target_z": -0.041503921171966295, "ce": 6.372091293334961, "genuineness": 4.432034492492676, "identity": 0.5176655054092407, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/f49666bdd21d31721fe955a6.mp3" }, { "key": "original-emo_Longing-de-1-seed1702-scale0.0", "bucket": "emo_Longing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "3dcd86b1b2af6e2cbb0c8b056de1500c64bc6a8cf4a4b8cc9a4df3c820724dc3", "task_id": "emo_Longing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6971279978752136, "target_z": 0.4121093709719846, "ce": 6.300607204437256, "genuineness": 4.381826400756836, "identity": 0.5487518310546875, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/b9d51346e46d0e5fd2575009.mp3" }, { "key": "original-emo_Longing-de-1-seed1702-scale0.5", "bucket": "emo_Longing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "2c0668fea1fd7fffedc4a842a7b74f8826e5a811fe6b7d90a0e5cce444dc7f0d", "task_id": "emo_Longing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3816962242126465, "target_z": -0.08398436218358724, "ce": 6.38003396987915, "genuineness": 4.042920112609863, "identity": 0.6154588460922241, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/131ad34ca29b295841518746.mp3" }, { "key": "original-emo_Longing-de-1-seed1702-scale0.75", "bucket": "emo_Longing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "02d20399f8a22554f013e5fe42abab7d24fbe925700b075998b02691df92876a", "task_id": "emo_Longing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.518921434879303, "target_z": 0.13183589667057075, "ce": 6.419747352600098, "genuineness": 4.3881025314331055, "identity": 0.5362563133239746, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/330dbd18f8efa2371402afaf.mp3" }, { "key": "original-emo_Longing-de-1-seed1702-scale1.0", "bucket": "emo_Longing", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "8722b91f8daa5ec8e60e5d26bc1d52cdb85624e2ecb5a3d9724b6a5bcc2c1788", "task_id": "emo_Longing-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5369284152984619, "target_z": 0.16015628442122287, "ce": 6.427689552307129, "genuineness": 4.570107460021973, "identity": 0.5528509020805359, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/de/66a08d4e6e5772cf484eca3c.mp3" }, { "key": "original-emo_Longing-en-0-seed1701-scale0.0", "bucket": "emo_Longing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "65be83076dbae2ef30d5750d3cc3fd27b7042b59f7eaa20b21bd07952d164b92", "task_id": "emo_Longing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.10972943902015686, "target_z": -0.5117187536618322, "ce": 6.38003396987915, "genuineness": 3.9550557136535645, "identity": 0.23239028453826904, "hypothesis": "The 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_Longing/en/3bec9d0bd7c6f609f0ef15dc.mp3" }, { "key": "original-emo_Longing-en-0-seed1701-scale0.5", "bucket": "emo_Longing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "66a4febb237ce556f95be516db1fd8c8e5f415fdde7d1d1120416b1fc853c573", "task_id": "emo_Longing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.2214966118335724, "target_z": -0.33593749560580133, "ce": 6.24500846862793, "genuineness": 4.231201171875, "identity": 0.26671692728996277, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/52191b5ccc982eeae851e365.mp3" }, { "key": "original-emo_Longing-en-0-seed1701-scale0.75", "bucket": "emo_Longing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "ac2cccdd990983e62ff7e16c16d3ae785862cf7bc23dfe21acc045fe71dfcc92", "task_id": "emo_Longing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.2724127769470215, "target_z": -0.2558593533951899, "ce": 6.268836498260498, "genuineness": 4.093128204345703, "identity": 0.2031223475933075, "hypothesis": "The 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_Longing/en/8b262eb3b115cf4bdb8328e8.mp3" }, { "key": "original-emo_Longing-en-0-seed1701-scale1.0", "bucket": "emo_Longing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "4c44e72542989a34478ecbcfae1990fc66fb447a1f4aadf0991e0ca47f80cba6", "task_id": "emo_Longing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.32208704948425293, "target_z": -0.177734391478245, "ce": 6.316492557525635, "genuineness": 3.936227321624756, "identity": 0.2886787950992584, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/c755551fe51b83245cf76f6a.mp3" }, { "key": "original-emo_Longing-en-0-seed1702-scale0.0", "bucket": "emo_Longing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "98b62f9db699496ebf18424cf8ebe5ed87457018353c4d84ebaa312a9d71748f", "task_id": "emo_Longing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.13084101676940918, "target_z": -0.47851562609854964, "ce": 6.252951145172119, "genuineness": 4.149612903594971, "identity": -0.002730106934905052, "hypothesis": "The 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_Longing/en/ff5f902517e677c3a5f8278d.mp3" }, { "key": "original-emo_Longing-en-0-seed1702-scale0.5", "bucket": "emo_Longing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "73d576dc8f4248b8350200d49bd2da3ced25e2447b838d45da20a99623d45c18", "task_id": "emo_Longing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.11718058586120605, "target_z": -0.5, "ce": 6.23706579208374, "genuineness": 3.823258876800537, "identity": 0.2488110363483429, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/28dfaf0c7b740212ac6ac99d.mp3" }, { "key": "original-emo_Longing-en-0-seed1702-scale0.75", "bucket": "emo_Longing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "34171471d7cd8b793fcb0ac59302c3bef1f2cd0bc3fd748b2c563fcf896f1115", "task_id": "emo_Longing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.8250393271446228, "target_z": 0.613281269773894, "ce": 6.2767791748046875, "genuineness": 4.137060642242432, "identity": 0.17871521413326263, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/7c4c63479dd27269b47d51be.mp3" }, { "key": "original-emo_Longing-en-0-seed1702-scale1.0", "bucket": "emo_Longing", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "fc47bcddac1ae98c7fef864c8c3cc705c5714fc0a4cc37a79702b5dc24bedf50", "task_id": "emo_Longing-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.13084101676940918, "target_z": -0.47851562609854964, "ce": 6.133810997009277, "genuineness": 4.055472373962402, "identity": 0.2891311049461365, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/60e8b5e0d368ee7fbee56182.mp3" }, { "key": "original-emo_Longing-en-1-seed1701-scale0.0", "bucket": "emo_Longing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "772c61f49a6718bb7b5f95747ab0728723617590dfb10ceeb1cf149c4925161e", "task_id": "emo_Longing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3391683101654053, "target_z": 1.4218750380830552, "ce": 6.260893821716309, "genuineness": 4.2751336097717285, "identity": 0.4652111530303955, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/03b34e3f66f0f3ab71b5ac9f.mp3" }, { "key": "original-emo_Longing-en-1-seed1701-scale0.5", "bucket": "emo_Longing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "bb115a20e30df3f30ebc6d25969a9340a8f33aac330526dad370e889e39ca3c7", "task_id": "emo_Longing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.428581953048706, "target_z": 1.562499894539232, "ce": 6.435632705688477, "genuineness": 4.6705241203308105, "identity": 0.3849828243255615, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/976aa1ea4563994d7cd60269.mp3" }, { "key": "original-emo_Longing-en-1-seed1701-scale0.75", "bucket": "emo_Longing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "e99225709cab33213e51b324ee836ace45902c189354bd64ce9c145acea3b0ec", "task_id": "emo_Longing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4732887744903564, "target_z": 1.6328123227673206, "ce": 6.419747352600098, "genuineness": 4.457139015197754, "identity": 0.2489008903503418, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/2909fb01a585f3a43a996393.mp3" }, { "key": "original-emo_Longing-en-1-seed1701-scale1.0", "bucket": "emo_Longing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "65de42053fab85f6d392a331b5671e01e96d8f65da1db37655b2c482a66ce5c9", "task_id": "emo_Longing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.35903799533844, "target_z": 1.453124985352671, "ce": 6.41180419921875, "genuineness": 4.507347106933594, "identity": 0.2892555594444275, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/a501aaa0adce05540240bd9e.mp3" }, { "key": "original-emo_Longing-en-1-seed1702-scale0.0", "bucket": "emo_Longing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "d91321082fbae1e22799c8370fc028d3c91c03551e4b496cf606e5b0d0c4f761", "task_id": "emo_Longing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1603407859802246, "target_z": 1.1406249501990817, "ce": 6.41180419921875, "genuineness": 4.444586753845215, "identity": 0.3158506751060486, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/1449ac8f2e53e1b4042c90cf.mp3" }, { "key": "original-emo_Longing-en-1-seed1702-scale0.5", "bucket": "emo_Longing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "674e05c3e32da5857315a2e7fabc83f631977429c2139ad934c3c54564e81693", "task_id": "emo_Longing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0187690258026123, "target_z": 0.9179686774957221, "ce": 6.41180419921875, "genuineness": 4.268857479095459, "identity": 0.3148263990879059, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/fe77ba4f1eee23476600f3d0.mp3" }, { "key": "original-emo_Longing-en-1-seed1702-scale0.75", "bucket": "emo_Longing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "2e207211c81cb7409eb9adaaa12c17d362e74d57c3e0783a44ed99e764b16c66", "task_id": "emo_Longing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5776050090789795, "target_z": 1.7968751552616862, "ce": 6.348263263702393, "genuineness": 4.507347106933594, "identity": 0.36673930287361145, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/b5caa312c01160878cabc6f3.mp3" }, { "key": "original-emo_Longing-en-1-seed1702-scale1.0", "bucket": "emo_Longing", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "b10417fddee93db8cd1417cbadde7068c81a6890aa2c2eef057f17b19b54eff0", "task_id": "emo_Longing-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1255688667297363, "target_z": 1.0859375893487062, "ce": 6.4515180587768555, "genuineness": 4.3881025314331055, "identity": 0.46488747000694275, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/en/24825df76960814e880a7bc2.mp3" }, { "key": "original-emo_Longing-es-0-seed1701-scale0.0", "bucket": "emo_Longing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "64fd247ed0ad5262176dd4da6b11f03931a0c6be8bdaf3e752d5df6a9591a5f9", "task_id": "emo_Longing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.4273344874382019, "target_z": -0.012207013581659537, "ce": 6.1020402908325195, "genuineness": 4.356721878051758, "identity": 0.5686603784561157, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/9ed945b427255dd2ef1359ef.mp3" }, { "key": "original-emo_Longing-es-0-seed1701-scale0.5", "bucket": "emo_Longing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "4bba2fa5726d271a30200a6fdc5a0a1ee4fa74944301fc519f918e13750b06dd", "task_id": "emo_Longing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.0426691472530365, "target_z": -0.6171874897468698, "ce": 6.046441555023193, "genuineness": 4.20609712600708, "identity": 0.7506090402603149, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/1b7832809901bc6fe9a81b4a.mp3" }, { "key": "original-emo_Longing-es-0-seed1701-scale0.75", "bucket": "emo_Longing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "533ccf66811b787f3828f9062bce7d5421af08c3971538c840c79e50946240ed", "task_id": "emo_Longing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.3407149314880371, "target_z": -0.14843748388793823, "ce": 6.181467056274414, "genuineness": 4.469690799713135, "identity": 0.6871556639671326, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/3d5983d7b585220e42a5e543.mp3" }, { "key": "original-emo_Longing-es-0-seed1701-scale1.0", "bucket": "emo_Longing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "c07e99968e9429d6fe8e0e487977d553aa5a03fa4c3c3b6fa32c4b2e5a4847e7", "task_id": "emo_Longing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.5375493168830872, "target_z": 0.1611328042608775, "ce": 6.038498878479004, "genuineness": 3.9299514293670654, "identity": 0.6816850900650024, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/5b9e11a3b9d29d4961e89705.mp3" }, { "key": "original-emo_Longing-es-0-seed1702-scale0.0", "bucket": "emo_Longing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "ff5b3de277339272ce4bdbb31823bfe4ab03ed55971d7b0dcb077fce87248db5", "task_id": "emo_Longing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.2910406291484833, "target_z": -0.22656249267633555, "ce": 6.070269584655762, "genuineness": 4.469690799713135, "identity": 0.5746372938156128, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/2d345613df12891f4970b416.mp3" }, { "key": "original-emo_Longing-es-0-seed1702-scale0.5", "bucket": "emo_Longing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "d72f4728edfc05adf6bbd8c1721cc821b0ad1c0595c0258e8975bcd4eb9c4a18", "task_id": "emo_Longing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.4115007817745209, "target_z": -0.037109394407710765, "ce": 6.062326908111572, "genuineness": 4.162164688110352, "identity": 0.38042375445365906, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/1655c9513962d60d43d7fb16.mp3" }, { "key": "original-emo_Longing-es-0-seed1702-scale0.75", "bucket": "emo_Longing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "18d25d5aa95d8369e10fb778a839d53c7465b5bb23c288929e7325b4dfae0fe7", "task_id": "emo_Longing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.1445014476776123, "target_z": -0.45703125219709934, "ce": 5.967014789581299, "genuineness": 3.9927117824554443, "identity": 0.5856442451477051, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/819b1526afdd4f627d129f21.mp3" }, { "key": "original-emo_Longing-es-0-seed1702-scale1.0", "bucket": "emo_Longing", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "4794677aa35e1d5dfaf0d40b5a9a7518afb239a98b78501435ec8374ba90ae7e", "task_id": "emo_Longing-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.07247370481491089, "target_z": -0.5703125219709934, "ce": 6.117925643920898, "genuineness": 3.7918784618377686, "identity": 0.48991429805755615, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/2568387a4b775f85fabd8173.mp3" }, { "key": "original-emo_Longing-es-1-seed1701-scale0.0", "bucket": "emo_Longing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "b7aba863f2d8cc6f1aa035dca1e6705e836b7157035668e42f378be44bc69214", "task_id": "emo_Longing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.6337932348251343, "target_z": 0.3124999414106845, "ce": 6.054384231567383, "genuineness": 4.406930446624756, "identity": 0.5281639695167542, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/a92ed288a440c675a89a4b6a.mp3" }, { "key": "original-emo_Longing-es-1-seed1701-scale0.5", "bucket": "emo_Longing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "798df2bfe74251b549a9e7889c4e4030ea8f89f9f200b1818b1af9121c3588e4", "task_id": "emo_Longing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.33015912771224976, "target_z": -0.16503907110530572, "ce": 6.149696350097656, "genuineness": 4.444586753845215, "identity": 0.5206763744354248, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/dca6373bc154fb31155f9abd.mp3" }, { "key": "original-emo_Longing-es-1-seed1701-scale0.75", "bucket": "emo_Longing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "1ede5632f9ca23060f24b21ee8e88992590151f50f697ccd909ace76e12d9a7e", "task_id": "emo_Longing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.3382312059402466, "target_z": -0.15234375073236645, "ce": 6.24500846862793, "genuineness": 4.507347106933594, "identity": 0.42957112193107605, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/a2a57fb50f1eb309d0056b2b.mp3" }, { "key": "original-emo_Longing-es-1-seed1701-scale1.0", "bucket": "emo_Longing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "21d3503699bb204886bd207ad9dbdf40f8b9a3652105418e6cfe406899fd3ecc", "task_id": "emo_Longing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.07744115591049194, "target_z": -0.5624999882821369, "ce": 6.260893821716309, "genuineness": 4.143336772918701, "identity": 0.537768542766571, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/e82be71f6c604adc6967bf7c.mp3" }, { "key": "original-emo_Longing-es-1-seed1702-scale0.0", "bucket": "emo_Longing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "eb902887892a724124cf1e94cb0d0033c3366491e665389b9053c451baa87b8a", "task_id": "emo_Longing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.3102894127368927, "target_z": -0.19628906524637416, "ce": 6.149696350097656, "genuineness": 4.758388519287109, "identity": 0.598783016204834, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/f19dfaec157b27ab787dd6a5.mp3" }, { "key": "original-emo_Longing-es-1-seed1702-scale0.5", "bucket": "emo_Longing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "70068a2842081449dbc5b743d2ba17e311ebc1729a92101df9c0f372dc147070", "task_id": "emo_Longing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.5363074541091919, "target_z": 0.1591796708386634, "ce": 6.0305562019348145, "genuineness": 4.632867813110352, "identity": 0.5268422365188599, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/6120337d53692a2c2eb5323d.mp3" }, { "key": "original-emo_Longing-es-1-seed1702-scale0.75", "bucket": "emo_Longing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "9b0b7aef839b9349fc83be9fa9ea4b76f76adbf82612495e98140267990d113e", "task_id": "emo_Longing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.3857322633266449, "target_z": -0.0776367019971176, "ce": 5.967014789581299, "genuineness": 4.65797233581543, "identity": 0.8177109360694885, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/d6df8750244b9ad7d73579c8.mp3" }, { "key": "original-emo_Longing-es-1-seed1702-scale1.0", "bucket": "emo_Longing", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "be1d1b8d55473e57c629cb97bd40978e669e3d114f3d6088102e7c3da15154fd", "task_id": "emo_Longing-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.3875950276851654, "target_z": -0.07470704873524885, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.5758697986602783, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/es/9c8bf6544a907aab0117513e.mp3" }, { "key": "original-emo_Longing-fr-0-seed1701-scale0.0", "bucket": "emo_Longing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "cbaaa62930e664c554aefedf6774a307e2032b8d4297c25fd6b5f8dc78b1d5b2", "task_id": "emo_Longing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.06750628352165222, "target_z": -0.5781250087883973, "ce": 6.23706579208374, "genuineness": 4.369274139404297, "identity": 0.5575627088546753, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/d8a3a380ba77ee839be77fe8.mp3" }, { "key": "original-emo_Longing-fr-0-seed1701-scale0.5", "bucket": "emo_Longing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "d2e9fe3c88f7c3b9f93f9e643c466896a38f30f3541b604d9411554a59426201", "task_id": "emo_Longing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.2649616003036499, "target_z": -0.26757815392847456, "ce": 6.078212261199951, "genuineness": 4.319066047668457, "identity": 0.643654465675354, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/a5266141c07db8a92b24ebc4.mp3" }, { "key": "original-emo_Longing-fr-0-seed1701-scale0.75", "bucket": "emo_Longing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "556a865ba2c089944f5999213aa72de1c3a971feee508890380e221ed896566e", "task_id": "emo_Longing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.3633788228034973, "target_z": -0.11279296298261425, "ce": 6.165581703186035, "genuineness": 4.369274139404297, "identity": 0.74146968126297, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/f1ecd00de7f61819cc51f29b.mp3" }, { "key": "original-emo_Longing-fr-0-seed1701-scale1.0", "bucket": "emo_Longing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "fd72f096c4eaae24696f1d0997296caec3225a7e8255fc43a5c62f7b4dcf121c", "task_id": "emo_Longing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.3841799199581146, "target_z": -0.08007814221061144, "ce": 6.070269584655762, "genuineness": 4.3127899169921875, "identity": 0.8336096405982971, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/a630c77ce07c2c879f270e25.mp3" }, { "key": "original-emo_Longing-fr-0-seed1702-scale0.0", "bucket": "emo_Longing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "a3a66c6fae15bc2a9e09c45a9ff9abf4a6534f0fa604a195881678dcd164b91b", "task_id": "emo_Longing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.13580843806266785, "target_z": -0.47070313928114565, "ce": 6.165581703186035, "genuineness": 4.457139015197754, "identity": 0.670764684677124, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/383fac185391bf339da798f7.mp3" }, { "key": "original-emo_Longing-fr-0-seed1702-scale0.5", "bucket": "emo_Longing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "6ffdeb43a5756cfbebb947d40c2f16a3bbd3724209d3512dc2d1514e805cec90", "task_id": "emo_Longing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.17927345633506775, "target_z": -0.40234375073236645, "ce": 6.046441555023193, "genuineness": 4.344170093536377, "identity": 0.5559517741203308, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/2a75b97c63a2ca0d036a2db0.mp3" }, { "key": "original-emo_Longing-fr-0-seed1702-scale0.75", "bucket": "emo_Longing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "643557182e3b0a45e76e4cc429c89b2a2dfb10eda14fc00937020b81b0a03516", "task_id": "emo_Longing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.4087066054344177, "target_z": -0.041503921171966295, "ce": 6.229123115539551, "genuineness": 4.444586753845215, "identity": 0.758037269115448, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/270277297da02b6fdefd7ab0.mp3" }, { "key": "original-emo_Longing-fr-0-seed1702-scale1.0", "bucket": "emo_Longing", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "45202b1b7eedf14cd9b9fabc73b60790c9494372e9fb6ab7f3cb28f0bebd9074", "task_id": "emo_Longing-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.07495743036270142, "target_z": -0.5664062551265651, "ce": 6.054384231567383, "genuineness": 4.306513786315918, "identity": 0.6803575754165649, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/13c854571ed2e77953b30a68.mp3" }, { "key": "original-emo_Longing-fr-1-seed1701-scale0.0", "bucket": "emo_Longing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "8d7f0ee66e48ae1496133f052c11ca397a62b9f66ff85c1d84581725e075668f", "task_id": "emo_Longing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.9343227744102478, "target_z": 0.7851562609854966, "ce": 6.197352409362793, "genuineness": 4.532451152801514, "identity": 0.7042949199676514, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/d85a828165f89f0c1e7ad86b.mp3" }, { "key": "original-emo_Longing-fr-1-seed1701-scale0.5", "bucket": "emo_Longing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "3211f673cd653ce56685e6eb1fdc3fd339288f85c641a3dc9f3e88038e8bad01", "task_id": "emo_Longing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 1.1106665134429932, "target_z": 1.0624999882821369, "ce": 6.165581703186035, "genuineness": 4.394378662109375, "identity": 0.7170595526695251, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/ab55c3a8eed3af00f2b877e1.mp3" }, { "key": "original-emo_Longing-fr-1-seed1701-scale0.75", "bucket": "emo_Longing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "856c032db5286f5fb2b30eb93c37b044df483dee4a24911a94294d91ee73f31e", "task_id": "emo_Longing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 1.3689727783203125, "target_z": 1.4687498652445743, "ce": 6.268836498260498, "genuineness": 4.444586753845215, "identity": 0.6269612908363342, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/6a41e8556dad095ec9225a5f.mp3" }, { "key": "original-emo_Longing-fr-1-seed1701-scale1.0", "bucket": "emo_Longing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "fbcb07d8a1256d315ff16df7a345b1ff31df6b7f8d61fbe6aabbc8885e4dc8cd", "task_id": "emo_Longing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 1.1603407859802246, "target_z": 1.1406249501990817, "ce": 6.173524379730225, "genuineness": 4.7081804275512695, "identity": 0.8363298773765564, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/e55b34ca7b80b3398b9fc20e.mp3" }, { "key": "original-emo_Longing-fr-1-seed1702-scale0.0", "bucket": "emo_Longing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "994e11c086d41eb90b7eb626ff92cd6b5002348d81fa6e8f8b997a5098faeedd", "task_id": "emo_Longing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 1.0013830661773682, "target_z": 0.8906249970705342, "ce": 6.022613525390625, "genuineness": 4.381826400756836, "identity": 0.7060984373092651, "hypothesis": "J'ai rouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/b3d8ff339588e2bad370da35.mp3" }, { "key": "original-emo_Longing-fr-1-seed1702-scale0.5", "bucket": "emo_Longing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "10d02e4b9c826ed304f4d45954b6fe4a8b5b403d3edf39f0cbb948bdc849d2c3", "task_id": "emo_Longing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.8747135996818542, "target_z": 0.6914062316908389, "ce": 6.23706579208374, "genuineness": 4.557555198669434, "identity": 0.7967464923858643, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/1ade218e36c968f18ec90e07.mp3" }, { "key": "original-emo_Longing-fr-1-seed1702-scale0.75", "bucket": "emo_Longing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "e8385993011a4e339a3e718023348c96cc04a611f3a6398b8efec9cf1d491e47", "task_id": "emo_Longing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 1.4931585788726807, "target_z": 1.6640624575227463, "ce": 6.109982967376709, "genuineness": 4.6956281661987305, "identity": 0.763183057308197, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/eb2d452526aa746688dddd15.mp3" }, { "key": "original-emo_Longing-fr-1-seed1702-scale1.0", "bucket": "emo_Longing", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "7b828932e6c0131e16b49de4354226f4e00976c937da0cb55d2402b4ab7af421", "task_id": "emo_Longing-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 1.0709271430969238, "target_z": 1.0000000937429048, "ce": 6.149696350097656, "genuineness": 4.425758361816406, "identity": 0.6127381324768066, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/fr/3cd3d86c5d4c75e187334295.mp3" }, { "key": "original-emo_Longing-nl-0-seed1701-scale0.0", "bucket": "emo_Longing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "d49c85b67d16d35bee96bfaa924e2023820f5ec98715906369ced1987bba5d58", "task_id": "emo_Longing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.0426691472530365, "target_z": -0.6171874897468698, "ce": 6.1020402908325195, "genuineness": 4.20609712600708, "identity": 0.645983874797821, "hypothesis": "De deur 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_Longing/nl/eb95ef26ffa5ab03a6c30e4b.mp3" }, { "key": "original-emo_Longing-nl-0-seed1701-scale0.5", "bucket": "emo_Longing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "8837cb255e84429b54193dba395d0f03dfbba63e758a4ee6047bc32bc35ce833", "task_id": "emo_Longing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.05012029409408569, "target_z": -0.6054687360850376, "ce": 5.982900142669678, "genuineness": 4.243753433227539, "identity": 0.7701873779296875, "hypothesis": "De deur staat nog hopen. 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/audio/emo_Longing/nl/c2be2a1d0eb546881c5b9c1a.mp3" }, { "key": "original-emo_Longing-nl-0-seed1701-scale0.75", "bucket": "emo_Longing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "43d154c914e8d9846361bba79a582ef5df774c8803b182ddf49684dedf25580d", "task_id": "emo_Longing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.0426691472530365, "target_z": -0.6171874897468698, "ce": 6.260893821716309, "genuineness": 4.143336772918701, "identity": 0.6267191171646118, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/07e1c6fb0e6783383b524c88.mp3" }, { "key": "original-emo_Longing-nl-0-seed1701-scale1.0", "bucket": "emo_Longing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "e1e689b75b360b419b540714631200647b57e114bda6b187ef2ace23b5b934c0", "task_id": "emo_Longing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.02776685357093811, "target_z": -0.6406249970705342, "ce": 5.95112943649292, "genuineness": 4.20609712600708, "identity": 0.6206000447273254, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/04421c50156676eb2ae916cc.mp3" }, { "key": "original-emo_Longing-nl-0-seed1702-scale0.0", "bucket": "emo_Longing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "283173a3e41acf7819d917320e6123b78545b8a77804dd1c2452afcc09c273b9", "task_id": "emo_Longing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.03273427486419678, "target_z": -0.6328125102531302, "ce": 6.022613525390625, "genuineness": 4.394378662109375, "identity": 0.4915071129798889, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/288d0e852ddb8a6044fcf98e.mp3" }, { "key": "original-emo_Longing-nl-0-seed1702-scale0.5", "bucket": "emo_Longing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "31c9317c2c6e084ed8cfe42ca062406e33850c4cea747feb4c226c790db07dc6", "task_id": "emo_Longing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.015348285436630249, "target_z": -0.6601562375497705, "ce": 6.109982967376709, "genuineness": 4.168440818786621, "identity": 0.7243484258651733, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/fa6946410f58687693d11726.mp3" }, { "key": "original-emo_Longing-nl-0-seed1702-scale0.75", "bucket": "emo_Longing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "145f61c634620b1d2a9403eb6faaebf50a827d67fdb9d62c0b4fb38adc04eb1e", "task_id": "emo_Longing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.07247370481491089, "target_z": -0.5703125219709934, "ce": 6.0305562019348145, "genuineness": 4.231201171875, "identity": 0.611470103263855, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/071536c51dff50fc0604acd5.mp3" }, { "key": "original-emo_Longing-nl-0-seed1702-scale1.0", "bucket": "emo_Longing", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "b4624d298562fafd95acc67afef28f9185eba40363ca0b56d1a4b29ba0dd5f71", "task_id": "emo_Longing-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.047636568546295166, "target_z": -0.6093750029294658, "ce": 5.959072113037109, "genuineness": 4.331617832183838, "identity": 0.3002551198005676, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/295f8ec1ed5eb4a76ab591cb.mp3" }, { "key": "original-emo_Longing-nl-1-seed1701-scale0.0", "bucket": "emo_Longing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "291ede74931bbe1db3c0b39501b4f5cdfeca54e5606a802eb081530ec2e47fed", "task_id": "emo_Longing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.09482714533805847, "target_z": -0.5351562609854966, "ce": 6.173524379730225, "genuineness": 4.444586753845215, "identity": 0.568903386592865, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/35073ab2078e51425ba8c7e1.mp3" }, { "key": "original-emo_Longing-nl-1-seed1701-scale0.5", "bucket": "emo_Longing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "922003ce07633b1acb5f900d82c314f37773e997c42b4f12f3d4baac3ae59b56", "task_id": "emo_Longing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.05260398983955383, "target_z": -0.6015625161120618, "ce": 6.141753673553467, "genuineness": 4.413206577301025, "identity": 0.7403442859649658, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/354d7ad09192b8415a9d2db4.mp3" }, { "key": "original-emo_Longing-nl-1-seed1701-scale0.75", "bucket": "emo_Longing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "d2b68ce55e8e27a0357e5b8d7b040a2242a2022c1bf711a1d6c1361d2f73d00e", "task_id": "emo_Longing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.022799432277679443, "target_z": -0.6484374838879382, "ce": 6.125868320465088, "genuineness": 4.306513786315918, "identity": 0.6198900938034058, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/e2331bec1a6adeabbdd3ab3a.mp3" }, { "key": "original-emo_Longing-nl-1-seed1701-scale1.0", "bucket": "emo_Longing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "0d142c489feb847118ddd28086b886986155c405148fd9e80da948e562036d0c", "task_id": "emo_Longing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.03273427486419678, "target_z": -0.6328125102531302, "ce": 6.133810997009277, "genuineness": 4.262581825256348, "identity": 0.6669306755065918, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/96ff7cbfb8fdd65c1d2cc185.mp3" }, { "key": "original-emo_Longing-nl-1-seed1702-scale0.0", "bucket": "emo_Longing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "ca6043224297999b6fed0beb17769fcb92f82f9f5cc4452980f1a08b60e8aa57", "task_id": "emo_Longing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.04515284299850464, "target_z": -0.613281269773894, "ce": 6.149696350097656, "genuineness": 4.432034492492676, "identity": 0.42914557456970215, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/ae943813514b850cb5d243b9.mp3" }, { "key": "original-emo_Longing-nl-1-seed1702-scale0.5", "bucket": "emo_Longing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "c54c6174368e10ea8227de04e6f81d9813ccd4b30452d38784ab249e9a00ee6a", "task_id": "emo_Longing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.030250579118728638, "target_z": -0.636718730226106, "ce": 6.205295085906982, "genuineness": 4.256305694580078, "identity": 0.6842216849327087, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/3abe836cf834b62a8a4587c5.mp3" }, { "key": "original-emo_Longing-nl-1-seed1702-scale0.75", "bucket": "emo_Longing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "19c5e5f38c80f768c578ca2a15e93e3f5d8a3e6f87a496f6b1d63a5b196fdcfc", "task_id": "emo_Longing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.06750628352165222, "target_z": -0.5781250087883973, "ce": 6.24500846862793, "genuineness": 4.507347106933594, "identity": 0.6210259199142456, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het Oude Raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/bcd7161322438eb3278bf1b3.mp3" }, { "key": "original-emo_Longing-nl-1-seed1702-scale1.0", "bucket": "emo_Longing", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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 Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "95bccd9868c96f0b16b69c4b53715f3bd9f0e54ca74bbf9412e39677e6523fcd", "mp3_sha256": "7bd97483ac38a0a5943908e5d1c9f9ae83912448529a429031f74953c07a23ba", "task_id": "emo_Longing-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Longing. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Longing. 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 Longing. 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 Longing. 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": 0.022799432277679443, "target_z": -0.6484374838879382, "ce": 6.109982967376709, "genuineness": 4.243753433227539, "identity": 0.6899545192718506, "hypothesis": "ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Longing/nl/960c6f670a43c121137c692c.mp3" } ], "source_standard_audio_unchanged": true }